diff options
157 files changed, 1991 insertions, 873 deletions
diff --git a/Documentation/arch/x86/sva.rst b/Documentation/arch/x86/sva.rst index 33cb05005982..6a759984d471 100644 --- a/Documentation/arch/x86/sva.rst +++ b/Documentation/arch/x86/sva.rst @@ -25,7 +25,7 @@ to cache translations for virtual addresses. The IOMMU driver uses the mmu_notifier() support to keep the device TLB cache and the CPU cache in sync. When an ATS lookup fails for a virtual address, the device should use the PRI in order to request the virtual address to be paged into the -CPU page tables. The device must use ATS again in order the fetch the +CPU page tables. The device must use ATS again in order to fetch the translation before use. Shared Hardware Workqueues @@ -216,7 +216,7 @@ submitting work and processing completions. Single Root I/O Virtualization (SR-IOV) focuses on providing independent hardware interfaces for virtualizing hardware. Hence, it's required to be -almost fully functional interface to software supporting the traditional +an almost fully functional interface to software supporting the traditional BARs, space for interrupts via MSI-X, its own register layout. Virtual Functions (VFs) are assisted by the Physical Function (PF) driver. diff --git a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml index 932f981265cc..52016a141227 100644 --- a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml +++ b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml @@ -53,11 +53,17 @@ properties: reg: maxItems: 1 + power-controller: + type: object + + reboot-mode: + type: object + required: - compatible - reg -additionalProperties: true +additionalProperties: false examples: - | diff --git a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml index 0bed37a994c3..e1f4d7c35a88 100644 --- a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml +++ b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml @@ -33,6 +33,10 @@ properties: clocks: maxItems: 1 + clock-names: + items: + - const: nf_clk + dmas: maxItems: 1 @@ -51,6 +55,7 @@ required: - reg-names - interrupts - clocks + - clock-names unevaluatedProperties: false @@ -66,7 +71,8 @@ examples: #address-cells = <1>; #size-cells = <0>; interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&nf_clk>; + clocks = <&clk>; + clock-names = "nf_clk"; cdns,board-delay-ps = <4830>; nand@0 { diff --git a/Documentation/networking/strparser.rst b/Documentation/networking/strparser.rst index 6cab1f74ae05..7f623d1db72a 100644 --- a/Documentation/networking/strparser.rst +++ b/Documentation/networking/strparser.rst @@ -112,7 +112,7 @@ Functions Callbacks ========= -There are six callbacks: +There are seven callbacks: :: @@ -184,6 +184,13 @@ There are six callbacks: :: + int (*read_sock)(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); + + The read_sock callback is used by strparser instead of + sock->ops->read_sock, if provided. + :: + int (*read_sock_done)(struct strparser *strp, int err); read_sock_done is called when the stream parser is done reading diff --git a/MAINTAINERS b/MAINTAINERS index 4e17764cb6ed..4ff26fa94895 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2210,6 +2210,7 @@ F: sound/soc/codecs/ssm3515.c ARM/APPLE MACHINE SUPPORT M: Sven Peter <sven@svenpeter.dev> +M: Janne Grunau <j@jannau.net> R: Alyssa Rosenzweig <alyssa@rosenzweig.io> L: asahi@lists.linux.dev L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@ -2284,7 +2285,7 @@ F: drivers/irqchip/irq-aspeed-i2c-ic.c ARM/ASPEED MACHINE SUPPORT M: Joel Stanley <joel@jms.id.au> -R: Andrew Jeffery <andrew@codeconstruct.com.au> +M: Andrew Jeffery <andrew@codeconstruct.com.au> L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-aspeed@lists.ozlabs.org (moderated for non-subscribers) S: Supported @@ -7425,7 +7426,6 @@ F: Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml F: drivers/gpu/drm/panel/panel-novatek-nt36672a.c DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS -M: Karol Herbst <kherbst@redhat.com> M: Lyude Paul <lyude@redhat.com> M: Danilo Krummrich <dakr@kernel.org> L: dri-devel@lists.freedesktop.org @@ -9829,8 +9829,7 @@ F: drivers/input/touchscreen/goodix* GOOGLE ETHERNET DRIVERS M: Jeroen de Borst <jeroendb@google.com> -M: Praveen Kaligineedi <pkaligineedi@google.com> -R: Shailend Chand <shailend@google.com> +M: Harshitha Ramamurthy <hramamurthy@google.com> L: netdev@vger.kernel.org S: Maintained F: Documentation/networking/device_drivers/ethernet/google/gve.rst @@ -16472,6 +16471,12 @@ F: net/ethtool/cabletest.c F: tools/testing/selftests/drivers/net/*/ethtool* K: cable_test +NETWORKING [ETHTOOL MAC MERGE] +M: Vladimir Oltean <vladimir.oltean@nxp.com> +F: net/ethtool/mm.c +F: tools/testing/selftests/drivers/net/hw/ethtool_mm.sh +K: ethtool_mm + NETWORKING [GENERAL] M: "David S. Miller" <davem@davemloft.net> M: Eric Dumazet <edumazet@google.com> @@ -19874,7 +19879,7 @@ F: net/rds/ F: tools/testing/selftests/net/rds/ RDT - RESOURCE ALLOCATION -M: Fenghua Yu <fenghua.yu@intel.com> +M: Tony Luck <tony.luck@intel.com> M: Reinette Chatre <reinette.chatre@intel.com> L: linux-kernel@vger.kernel.org S: Supported @@ -24064,7 +24069,6 @@ F: tools/testing/selftests/ftrace/ TRACING MMIO ACCESSES (MMIOTRACE) M: Steven Rostedt <rostedt@goodmis.org> M: Masami Hiramatsu <mhiramat@kernel.org> -R: Karol Herbst <karolherbst@gmail.com> R: Pekka Paalanen <ppaalanen@gmail.com> L: linux-kernel@vger.kernel.org L: nouveau@lists.freedesktop.org diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts index e4517f47d519..eb9470a00e54 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts @@ -226,7 +226,6 @@ }; &uart5 { - pinctrl-0 = <&uart5_xfer>; rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>; status = "okay"; }; diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi index ae050cc6cd05..e80412abec08 100644 --- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi @@ -396,6 +396,12 @@ status = "okay"; }; +&uart5 { + /delete-property/ dmas; + /delete-property/ dma-names; + pinctrl-0 = <&uart5_xfer>; +}; + /* Mule UCAN */ &usb_host0_ehci { status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts index 67c246ad8b8c..ec2ce894da1f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts @@ -17,8 +17,7 @@ &gmac2io { phy-handle = <&yt8531c>; - tx_delay = <0x19>; - rx_delay = <0x05>; + phy-mode = "rgmii-id"; status = "okay"; mdio { diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts index 324a8e951f7e..846b931e16d2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts @@ -15,6 +15,7 @@ &gmac2io { phy-handle = <&rtl8211e>; + phy-mode = "rgmii"; tx_delay = <0x24>; rx_delay = <0x18>; status = "okay"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi index 4f193704e5dc..09508e324a28 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi @@ -109,7 +109,6 @@ assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>; assigned-clock-parents = <&gmac_clk>, <&gmac_clk>; clock_in_out = "input"; - phy-mode = "rgmii"; phy-supply = <&vcc_io>; pinctrl-0 = <&rgmiim1_pins>; pinctrl-names = "default"; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi index 988e6ca32fac..a9ea4b0daa04 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi @@ -22,11 +22,11 @@ }; /* EC turns on w/ pp900_usb_en */ - pp900_usb: pp900-ap { + pp900_usb: regulator-pp900-ap { }; /* EC turns on w/ pp900_pcie_en */ - pp900_pcie: pp900-ap { + pp900_pcie: regulator-pp900-ap { }; pp3000: regulator-pp3000 { @@ -126,7 +126,7 @@ }; /* Always on; plain and simple */ - pp3000_ap: pp3000_emmc: pp3000 { + pp3000_ap: pp3000_emmc: regulator-pp3000 { }; pp1500_ap_io: regulator-pp1500-ap-io { @@ -160,7 +160,7 @@ }; /* EC turns on w/ pp3300_usb_en_l */ - pp3300_usb: pp3300 { + pp3300_usb: regulator-pp3300 { }; /* gpio is shared with pp1800_pcie and pinctrl is set there */ diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi index 19b23b438965..5e068377a0a2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi @@ -92,7 +92,7 @@ }; /* EC turns on pp1800_s3_en */ - pp1800_s3: pp1800 { + pp1800_s3: regulator-pp1800 { }; /* pp3300 children, sorted by name */ @@ -109,11 +109,11 @@ }; /* EC turns on pp3300_s0_en */ - pp3300_s0: pp3300 { + pp3300_s0: regulator-pp3300 { }; /* EC turns on pp3300_s3_en */ - pp3300_s3: pp3300 { + pp3300_s3: regulator-pp3300 { }; /* diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi index 6d9e60b01225..7eca1da78cff 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi @@ -189,39 +189,39 @@ }; /* EC turns on w/ pp900_ddrpll_en */ - pp900_ddrpll: pp900-ap { + pp900_ddrpll: regulator-pp900-ap { }; /* EC turns on w/ pp900_pll_en */ - pp900_pll: pp900-ap { + pp900_pll: regulator-pp900-ap { }; /* EC turns on w/ pp900_pmu_en */ - pp900_pmu: pp900-ap { + pp900_pmu: regulator-pp900-ap { }; /* EC turns on w/ pp1800_s0_en_l */ - pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: pp1800 { + pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: regulator-pp1800 { }; /* EC turns on w/ pp1800_avdd_en_l */ - pp1800_avdd: pp1800 { + pp1800_avdd: regulator-pp1800 { }; /* EC turns on w/ pp1800_lid_en_l */ - pp1800_lid: pp1800_mic: pp1800 { + pp1800_lid: pp1800_mic: regulator-pp1800 { }; /* EC turns on w/ lpddr_pwr_en */ - pp1800_lpddr: pp1800 { + pp1800_lpddr: regulator-pp1800 { }; /* EC turns on w/ pp1800_pmu_en_l */ - pp1800_pmu: pp1800 { + pp1800_pmu: regulator-pp1800 { }; /* EC turns on w/ pp1800_usb_en_l */ - pp1800_usb: pp1800 { + pp1800_usb: regulator-pp1800 { }; pp3000_sd_slot: regulator-pp3000-sd-slot { @@ -259,11 +259,11 @@ }; /* EC turns on w/ pp3300_trackpad_en_l */ - pp3300_trackpad: pp3300-trackpad { + pp3300_trackpad: regulator-pp3300-trackpad { }; /* EC turns on w/ usb_a_en */ - pp5000_usb_a_vbus: pp5000 { + pp5000_usb_a_vbus: regulator-pp5000 { }; ap_rtc_clk: ap-rtc-clk { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi index 8cfa30837ce7..c3abdfb04f8f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi @@ -549,10 +549,10 @@ mmu600_pcie: iommu@fc900000 { compatible = "arm,smmu-v3"; reg = <0x0 0xfc900000 0x0 0x200000>; - interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 369 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 371 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 374 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 367 IRQ_TYPE_EDGE_RISING 0>; interrupt-names = "eventq", "gerror", "priq", "cmdq-sync"; #iommu-cells = <1>; }; @@ -560,10 +560,10 @@ mmu600_php: iommu@fcb00000 { compatible = "arm,smmu-v3"; reg = <0x0 0xfcb00000 0x0 0x200000>; - interrupts = <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH 0>, - <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH 0>; + interrupts = <GIC_SPI 381 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 383 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 386 IRQ_TYPE_EDGE_RISING 0>, + <GIC_SPI 379 IRQ_TYPE_EDGE_RISING 0>; interrupt-names = "eventq", "gerror", "priq", "cmdq-sync"; #iommu-cells = <1>; status = "disabled"; @@ -2668,9 +2668,9 @@ rockchip,hw-tshut-temp = <120000>; rockchip,hw-tshut-mode = <0>; /* tshut mode 0:CRU 1:GPIO */ rockchip,hw-tshut-polarity = <0>; /* tshut polarity 0:LOW 1:HIGH */ - pinctrl-0 = <&tsadc_gpio_func>; - pinctrl-1 = <&tsadc_shut>; - pinctrl-names = "gpio", "otpout"; + pinctrl-0 = <&tsadc_shut_org>; + pinctrl-1 = <&tsadc_gpio_func>; + pinctrl-names = "default", "sleep"; #thermal-sensor-cells = <1>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts index 92f0ed83c990..bc6b43a77153 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts @@ -113,7 +113,7 @@ compatible = "regulator-fixed"; regulator-name = "vcc3v3_lcd"; enable-active-high; - gpio = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>; + gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>; pinctrl-names = "default"; pinctrl-0 = <&lcdpwr_en>; vin-supply = <&vcc3v3_sys>; @@ -241,7 +241,7 @@ &pinctrl { lcd { lcdpwr_en: lcdpwr-en { - rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>; + rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>; }; bl_en: bl-en { diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi index 4a950907ea6f..840b638af1c2 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi @@ -213,7 +213,6 @@ interrupt-names = "sys", "pmc", "msg", "legacy", "err", "dma0", "dma1", "dma2", "dma3"; max-link-speed = <3>; - iommus = <&mmu600_pcie 0x0000>; num-lanes = <4>; phys = <&pcie30phy>; phy-names = "pcie-phy"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso index 672d748fcc67..f229cb49da68 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso @@ -23,3 +23,7 @@ vpcie3v3-supply = <&vcc3v3_pcie30>; status = "okay"; }; + +&mmu600_pcie { + status = "disabled"; +}; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index cb7da4415599..1f25423de383 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -1551,6 +1551,8 @@ CONFIG_PWM_VISCONTI=m CONFIG_SL28CPLD_INTC=y CONFIG_QCOM_PDC=y CONFIG_QCOM_MPM=y +CONFIG_TI_SCI_INTR_IRQCHIP=y +CONFIG_TI_SCI_INTA_IRQCHIP=y CONFIG_RESET_GPIO=m CONFIG_RESET_IMX7=y CONFIG_RESET_QCOM_AOSS=y diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index 885bd1dd2c82..9276e0576d0a 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -86,7 +86,7 @@ static int cmma_test_essa(void) : [reg1] "=&d" (reg1), [reg2] "=&a" (reg2), [rc] "+&d" (rc), - [tmp] "=&d" (tmp), + [tmp] "+&d" (tmp), "+Q" (get_lowcore()->program_new_psw), "=Q" (old) : [psw_old] "a" (&old), diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig index 44f01a4bc810..80bdfbae6e5b 100644 --- a/arch/s390/configs/debug_defconfig +++ b/arch/s390/configs/debug_defconfig @@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set +CONFIG_MD_LINEAR=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -874,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_GRAPH_RETVAL=y +CONFIG_FUNCTION_GRAPH_RETADDR=y CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig index 8bcd37edd3c9..449a0e996b96 100644 --- a/arch/s390/configs/defconfig +++ b/arch/s390/configs/defconfig @@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m CONFIG_MD=y CONFIG_BLK_DEV_MD=y # CONFIG_MD_BITMAP_FILE is not set +CONFIG_MD_LINEAR=m CONFIG_MD_CLUSTER=m CONFIG_BCACHE=m CONFIG_BLK_DEV_DM=y @@ -825,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y CONFIG_BOOTTIME_TRACING=y CONFIG_FUNCTION_GRAPH_RETVAL=y +CONFIG_FUNCTION_GRAPH_RETADDR=y CONFIG_FPROBE=y CONFIG_FUNCTION_PROFILER=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile index bdcf2a3b6c41..bd39b36e7bd6 100644 --- a/arch/s390/purgatory/Makefile +++ b/arch/s390/purgatory/Makefile @@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE $(call if_changed_rule,cc_o_c) -CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY +CFLAGS_sha256.o := -D__NO_FORTIFY $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE $(call if_changed_rule,as_o_S) @@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common KBUILD_CFLAGS += -fno-stack-protector KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING +KBUILD_CFLAGS += -D__DISABLE_EXPORTS KBUILD_CFLAGS += $(CLANG_FLAGS) KBUILD_CFLAGS += $(call cc-option,-fno-PIE) KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS)) +KBUILD_AFLAGS += -D__DISABLE_EXPORTS # Since we link purgatory with -r unresolved symbols are not checked, so we # also link a purgatory.chk binary without -r to check for unresolved symbols. diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index e86333eee266..cdcebf30468a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = { METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6), METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7), + INTEL_EVENT_CONSTRAINT(0x20, 0xf), + + INTEL_UEVENT_CONSTRAINT(0x012a, 0xf), + INTEL_UEVENT_CONSTRAINT(0x012b, 0xf), INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), INTEL_UEVENT_CONSTRAINT(0x0175, 0x4), INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff), INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff), - /* - * Generally event codes < 0x90 are restricted to counters 0-3. - * The 0x2E and 0x3C are exception, which has no restriction. - */ - INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf), - INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf), - INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1), INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1), INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1), INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8), + INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc), INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3), - INTEL_EVENT_CONSTRAINT(0xce, 0x1), INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf), - /* - * Generally event codes >= 0x90 are likely to have no restrictions. - * The exception are defined as above. - */ - INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff), + + INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf), EVENT_CONSTRAINT_END }; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index c2e2eae7309c..f122882ef278 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), - INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff), + INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc), INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 8bd84114c2d9..df838e3bdbe0 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, + { X86_FEATURE_AVX_VNNI, X86_FEATURE_AVX }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, { X86_FEATURE_VAES, X86_FEATURE_AVX }, { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, diff --git a/block/blk-merge.c b/block/blk-merge.c index 15cd231d560c..c7c85e10cf9c 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -270,7 +270,7 @@ static bool bvec_split_segs(const struct queue_limits *lim, const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes, unsigned max_segs, unsigned max_bytes) { - unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; + unsigned max_len = max_bytes - *bytes; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; @@ -556,11 +556,14 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq, { struct req_iterator iter = { .bio = rq->bio, - .iter = rq->bio->bi_iter, }; struct phys_vec vec; int nsegs = 0; + /* the internal flush request may not have bio attached */ + if (iter.bio) + iter.iter = iter.bio->bi_iter; + while (blk_map_iter_next(rq, &iter, &vec)) { *last_sg = blk_next_sg(last_sg, sglist); sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len, diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c index 814b16bb1953..e5301fac1397 100644 --- a/drivers/accel/amdxdna/amdxdna_mailbox.c +++ b/drivers/accel/amdxdna/amdxdna_mailbox.c @@ -8,6 +8,7 @@ #include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/iopoll.h> +#include <linux/slab.h> #include <linux/xarray.h> #define CREATE_TRACE_POINTS diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c index fc92e43d0fe9..2ad53cc6aae5 100644 --- a/drivers/acpi/platform_profile.c +++ b/drivers/acpi/platform_profile.c @@ -417,8 +417,14 @@ static int profile_class_registered(struct device *dev, const void *data) static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx) { - if (!class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered)) + struct device *dev; + + dev = class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered); + if (!dev) return 0; + + put_device(dev); + return attr->mode; } diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index 53b2c7719dc5..91d44302eac9 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -651,8 +651,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev, * If no sub-node was found, keep this for device tree * compatibility */ - hpriv->mask_port_map |= BIT(0); - rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node); if (rc) goto err_out; diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c index a3fe98cd3838..82815428f8f9 100644 --- a/drivers/clocksource/jcore-pit.c +++ b/drivers/clocksource/jcore-pit.c @@ -114,6 +114,18 @@ static int jcore_pit_local_init(unsigned cpu) pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd); clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX); + enable_percpu_irq(pit->ced.irq, IRQ_TYPE_NONE); + + return 0; +} + +static int jcore_pit_local_teardown(unsigned cpu) +{ + struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu); + + pr_info("Local J-Core PIT teardown on cpu %u\n", cpu); + + disable_percpu_irq(pit->ced.irq); return 0; } @@ -168,6 +180,7 @@ static int __init jcore_pit_init(struct device_node *node) return -ENOMEM; } + irq_set_percpu_devid(pit_irq); err = request_percpu_irq(pit_irq, jcore_timer_interrupt, "jcore_pit", jcore_pit_percpu); if (err) { @@ -237,7 +250,7 @@ static int __init jcore_pit_init(struct device_node *node) cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING, "clockevents/jcore:starting", - jcore_pit_local_init, NULL); + jcore_pit_local_init, jcore_pit_local_teardown); return 0; } diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c index 83b69fc4fba5..a8915d3b4df5 100644 --- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c +++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c @@ -254,8 +254,8 @@ static int scmi_imx_misc_ctrl_set(const struct scmi_protocol_handle *ph, if (num > max_num) return -EINVAL; - ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, sizeof(*in), - 0, &t); + ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, + sizeof(*in) + num * sizeof(__le32), 0, &t); if (ret) return ret; diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig index 907cd149c40a..c964f4924359 100644 --- a/drivers/firmware/imx/Kconfig +++ b/drivers/firmware/imx/Kconfig @@ -25,6 +25,7 @@ config IMX_SCU config IMX_SCMI_MISC_DRV tristate "IMX SCMI MISC Protocol driver" + depends on ARCH_MXC || COMPILE_TEST default y if ARCH_MXC help The System Controller Management Interface firmware (SCMI FW) is diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index c4f34a347cb6..c36a9dbccd4d 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -36,6 +36,7 @@ struct vf610_gpio_port { struct clk *clk_port; struct clk *clk_gpio; int irq; + spinlock_t lock; /* protect gpio direction registers */ }; #define GPIO_PDOR 0x00 @@ -124,6 +125,7 @@ static int vf610_gpio_direction_input(struct gpio_chip *chip, unsigned int gpio) u32 val; if (port->sdata->have_paddr) { + guard(spinlock_irqsave)(&port->lock); val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); val &= ~mask; vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); @@ -142,6 +144,7 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned int gpio vf610_gpio_set(chip, gpio, value); if (port->sdata->have_paddr) { + guard(spinlock_irqsave)(&port->lock); val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); val |= mask; vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); @@ -297,6 +300,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) return -ENOMEM; port->sdata = device_get_match_data(dev); + spin_lock_init(&port->lock); dual_base = port->sdata->have_dual_base; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index ca2f58a2cd45..fc19df5a64c2 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -1057,8 +1057,19 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, desc->gdev = gdev; if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) { - assign_bit(FLAG_IS_OUT, - &desc->flags, !gc->get_direction(gc, desc_index)); + ret = gc->get_direction(gc, desc_index); + if (ret < 0) + /* + * FIXME: Bail-out here once all GPIO drivers + * are updated to not return errors in + * situations that can be considered normal + * operation. + */ + dev_warn(&gdev->dev, + "%s: get_direction failed: %d\n", + __func__, ret); + + assign_bit(FLAG_IS_OUT, &desc->flags, !ret); } else { assign_bit(FLAG_IS_OUT, &desc->flags, !gc->direction_input); @@ -2728,13 +2739,18 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc) if (guard.gc->direction_input) { ret = guard.gc->direction_input(guard.gc, gpio_chip_hwgpio(desc)); - } else if (guard.gc->get_direction && - (guard.gc->get_direction(guard.gc, - gpio_chip_hwgpio(desc)) != 1)) { - gpiod_warn(desc, - "%s: missing direction_input() operation and line is output\n", - __func__); - return -EIO; + } else if (guard.gc->get_direction) { + ret = guard.gc->get_direction(guard.gc, + gpio_chip_hwgpio(desc)); + if (ret < 0) + return ret; + + if (ret != GPIO_LINE_DIRECTION_IN) { + gpiod_warn(desc, + "%s: missing direction_input() operation and line is output\n", + __func__); + return -EIO; + } } if (ret == 0) { clear_bit(FLAG_IS_OUT, &desc->flags); @@ -2771,12 +2787,18 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value) gpio_chip_hwgpio(desc), val); } else { /* Check that we are in output mode if we can */ - if (guard.gc->get_direction && - guard.gc->get_direction(guard.gc, gpio_chip_hwgpio(desc))) { - gpiod_warn(desc, - "%s: missing direction_output() operation\n", - __func__); - return -EIO; + if (guard.gc->get_direction) { + ret = guard.gc->get_direction(guard.gc, + gpio_chip_hwgpio(desc)); + if (ret < 0) + return ret; + + if (ret != GPIO_LINE_DIRECTION_OUT) { + gpiod_warn(desc, + "%s: missing direction_output() operation\n", + __func__); + return -EIO; + } } /* * If we can't actively set the direction, we are some @@ -3129,6 +3151,8 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc) static int gpio_chip_get_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { + lockdep_assert_held(&gc->gpiodev->srcu); + if (gc->get_multiple) return gc->get_multiple(gc, mask, bits); if (gc->get) { @@ -3159,6 +3183,7 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep, struct gpio_array *array_info, unsigned long *value_bitmap) { + struct gpio_chip *gc; int ret, i = 0; /* @@ -3170,10 +3195,15 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep, array_size <= array_info->size && (void *)array_info == desc_array + array_info->size) { if (!can_sleep) - WARN_ON(array_info->chip->can_sleep); + WARN_ON(array_info->gdev->can_sleep); + + guard(srcu)(&array_info->gdev->srcu); + gc = srcu_dereference(array_info->gdev->chip, + &array_info->gdev->srcu); + if (!gc) + return -ENODEV; - ret = gpio_chip_get_multiple(array_info->chip, - array_info->get_mask, + ret = gpio_chip_get_multiple(gc, array_info->get_mask, value_bitmap); if (ret) return ret; @@ -3454,6 +3484,8 @@ static void gpiod_set_raw_value_commit(struct gpio_desc *desc, bool value) static void gpio_chip_set_multiple(struct gpio_chip *gc, unsigned long *mask, unsigned long *bits) { + lockdep_assert_held(&gc->gpiodev->srcu); + if (gc->set_multiple) { gc->set_multiple(gc, mask, bits); } else { @@ -3471,6 +3503,7 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep, struct gpio_array *array_info, unsigned long *value_bitmap) { + struct gpio_chip *gc; int i = 0; /* @@ -3482,14 +3515,19 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep, array_size <= array_info->size && (void *)array_info == desc_array + array_info->size) { if (!can_sleep) - WARN_ON(array_info->chip->can_sleep); + WARN_ON(array_info->gdev->can_sleep); + + guard(srcu)(&array_info->gdev->srcu); + gc = srcu_dereference(array_info->gdev->chip, + &array_info->gdev->srcu); + if (!gc) + return -ENODEV; if (!raw && !bitmap_empty(array_info->invert_mask, array_size)) bitmap_xor(value_bitmap, value_bitmap, array_info->invert_mask, array_size); - gpio_chip_set_multiple(array_info->chip, array_info->set_mask, - value_bitmap); + gpio_chip_set_multiple(gc, array_info->set_mask, value_bitmap); i = find_first_zero_bit(array_info->set_mask, array_size); if (i == array_size) @@ -4751,9 +4789,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, { struct gpio_desc *desc; struct gpio_descs *descs; + struct gpio_device *gdev; struct gpio_array *array_info = NULL; - struct gpio_chip *gc; int count, bitmap_size; + unsigned long dflags; size_t descs_size; count = gpiod_count(dev, con_id); @@ -4774,7 +4813,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, descs->desc[descs->ndescs] = desc; - gc = gpiod_to_chip(desc); + gdev = gpiod_to_gpio_device(desc); /* * If pin hardware number of array member 0 is also 0, select * its chip as a candidate for fast bitmap processing path. @@ -4782,8 +4821,8 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, if (descs->ndescs == 0 && gpio_chip_hwgpio(desc) == 0) { struct gpio_descs *array; - bitmap_size = BITS_TO_LONGS(gc->ngpio > count ? - gc->ngpio : count); + bitmap_size = BITS_TO_LONGS(gdev->ngpio > count ? + gdev->ngpio : count); array = krealloc(descs, descs_size + struct_size(array_info, invert_mask, 3 * bitmap_size), @@ -4803,7 +4842,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, array_info->desc = descs->desc; array_info->size = count; - array_info->chip = gc; + array_info->gdev = gdev; bitmap_set(array_info->get_mask, descs->ndescs, count - descs->ndescs); bitmap_set(array_info->set_mask, descs->ndescs, @@ -4816,7 +4855,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, continue; /* Unmark array members which don't belong to the 'fast' chip */ - if (array_info->chip != gc) { + if (array_info->gdev != gdev) { __clear_bit(descs->ndescs, array_info->get_mask); __clear_bit(descs->ndescs, array_info->set_mask); } @@ -4839,9 +4878,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, array_info->set_mask); } } else { + dflags = READ_ONCE(desc->flags); /* Exclude open drain or open source from fast output */ - if (gpiochip_line_is_open_drain(gc, descs->ndescs) || - gpiochip_line_is_open_source(gc, descs->ndescs)) + if (test_bit(FLAG_OPEN_DRAIN, &dflags) || + test_bit(FLAG_OPEN_SOURCE, &dflags)) __clear_bit(descs->ndescs, array_info->set_mask); /* Identify 'fast' pins which require invertion */ @@ -4853,7 +4893,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev, if (array_info) dev_dbg(dev, "GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n", - array_info->chip->label, array_info->size, + array_info->gdev->label, array_info->size, *array_info->get_mask, *array_info->set_mask, *array_info->invert_mask); return descs; diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h index 83690f72f7e5..147156ec502b 100644 --- a/drivers/gpio/gpiolib.h +++ b/drivers/gpio/gpiolib.h @@ -114,7 +114,7 @@ extern const char *const gpio_suffixes[]; * * @desc: Array of pointers to the GPIO descriptors * @size: Number of elements in desc - * @chip: Parent GPIO chip + * @gdev: Parent GPIO device * @get_mask: Get mask used in fastpath * @set_mask: Set mask used in fastpath * @invert_mask: Invert mask used in fastpath @@ -126,7 +126,7 @@ extern const char *const gpio_suffixes[]; struct gpio_array { struct gpio_desc **desc; unsigned int size; - struct gpio_chip *chip; + struct gpio_device *gdev; unsigned long *get_mask; unsigned long *set_mask; unsigned long invert_mask[]; diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index c977b74f82f0..82bf6c654de2 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -809,8 +809,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder, /* select data lane width */ tmp = intel_de_read(display, TRANS_DDI_FUNC_CTL(display, dsi_trans)); - tmp &= ~DDI_PORT_WIDTH_MASK; - tmp |= DDI_PORT_WIDTH(intel_dsi->lane_count); + tmp &= ~TRANS_DDI_PORT_WIDTH_MASK; + tmp |= TRANS_DDI_PORT_WIDTH(intel_dsi->lane_count); /* select input pipe */ tmp &= ~TRANS_DDI_EDP_INPUT_MASK; diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index acb986bc1f33..18c66992aa1d 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -658,7 +658,6 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST); u32 ctl; if (DISPLAY_VER(dev_priv) >= 11) @@ -678,8 +677,7 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK); if (DISPLAY_VER(dev_priv) >= 12) { - if (!intel_dp_mst_is_master_trans(crtc_state) || - (!is_mst && intel_dp_is_uhbr(crtc_state))) { + if (!intel_dp_mst_is_master_trans(crtc_state)) { ctl &= ~(TGL_TRANS_DDI_PORT_MASK | TRANS_DDI_MODE_SELECT_MASK); } @@ -3134,7 +3132,7 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state, intel_dp_set_power(intel_dp, DP_SET_POWER_D3); if (DISPLAY_VER(dev_priv) >= 12) { - if (is_mst) { + if (is_mst || intel_dp_is_uhbr(old_crtc_state)) { enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder; intel_de_rmw(dev_priv, @@ -3487,7 +3485,7 @@ static void intel_ddi_enable_hdmi(struct intel_atomic_state *state, intel_de_rmw(dev_priv, XELPDP_PORT_BUF_CTL1(dev_priv, port), XELPDP_PORT_WIDTH_MASK | XELPDP_PORT_REVERSAL, port_buf); - buf_ctl |= DDI_PORT_WIDTH(lane_count); + buf_ctl |= DDI_PORT_WIDTH(crtc_state->lane_count); if (DISPLAY_VER(dev_priv) >= 20) buf_ctl |= XE2LPD_DDI_BUF_D2D_LINK_ENABLE; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 4271da219b41..41128469f12a 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -6628,12 +6628,30 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state) { struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_plane_state *plane_state; struct intel_crtc_state *crtc_state; + struct intel_plane *plane; struct intel_crtc *crtc; u8 affected_pipes = 0; u8 modeset_pipes = 0; int i; + /* + * Any plane which is in use by the joiner needs its crtc. + * Pull those in first as this will not have happened yet + * if the plane remains disabled according to uapi. + */ + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + crtc = to_intel_crtc(plane_state->hw.crtc); + if (!crtc) + continue; + + crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + } + + /* Now pull in all joined crtcs */ for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) { affected_pipes |= crtc_state->joiner_pipes; if (intel_crtc_needs_modeset(crtc_state)) diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 8b1977cfec50..6696a32cdd3e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -1563,7 +1563,7 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp, if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) { lt_err(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clear\n"); - return false; + goto out; } if (intel_dp_128b132b_lane_eq(intel_dp, crtc_state) && @@ -1575,6 +1575,19 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp, passed ? "passed" : "failed", crtc_state->port_clock, crtc_state->lane_count); +out: + /* + * Ensure that the training pattern does get set to TPS2 even in case + * of a failure, as is the case at the end of a passing link training + * and what is expected by the transcoder. Leaving TPS1 set (and + * disabling the link train mode in DP_TP_CTL later from TPS1 directly) + * would result in a stuck transcoder HW state and flip-done timeouts + * later in the modeset sequence. + */ + if (!passed) + intel_dp_program_link_training_pattern(intel_dp, crtc_state, + DP_PHY_DPRX, DP_TRAINING_PATTERN_2); + return passed; } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index cc05bd9e43b4..3fce5c000144 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -3449,10 +3449,10 @@ static inline int guc_lrc_desc_unpin(struct intel_context *ce) */ ret = deregister_context(ce, ce->guc_id.id); if (ret) { - spin_lock(&ce->guc_state.lock); + spin_lock_irqsave(&ce->guc_state.lock, flags); set_context_registered(ce); clr_context_destroyed(ce); - spin_unlock(&ce->guc_state.lock); + spin_unlock_irqrestore(&ce->guc_state.lock, flags); /* * As gt-pm is awake at function entry, intel_wakeref_put_async merely decrements * the wakeref immediately but per function spec usage call this after unlock. diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 765e6c0528fb..786c727aea45 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3633,7 +3633,7 @@ enum skl_power_gate { #define DDI_BUF_IS_IDLE (1 << 7) #define DDI_BUF_CTL_TC_PHY_OWNERSHIP REG_BIT(6) #define DDI_A_4_LANES (1 << 4) -#define DDI_PORT_WIDTH(width) (((width) - 1) << 1) +#define DDI_PORT_WIDTH(width) (((width) == 3 ? 4 : ((width) - 1)) << 1) #define DDI_PORT_WIDTH_MASK (7 << 1) #define DDI_PORT_WIDTH_SHIFT 1 #define DDI_INIT_DISPLAY_DETECTED (1 << 0) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 65d38b25c070..699b0dd34b18 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -813,10 +813,10 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu) } ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION); - DRM_INFO("Loaded GMU firmware v%u.%u.%u\n", - FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver), - FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver), - FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver)); + DRM_INFO_ONCE("Loaded GMU firmware v%u.%u.%u\n", + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver), + FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver)); return 0; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h index 421afacb7248..36cc9dbc00b5 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h @@ -297,7 +297,7 @@ static const struct dpu_wb_cfg sm8150_wb[] = { { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, - .features = WB_SDM845_MASK, + .features = WB_SM8250_MASK, .format_list = wb2_formats_rgb, .num_formats = ARRAY_SIZE(wb2_formats_rgb), .clk_ctrl = DPU_CLK_CTRL_WB2, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h index 641023b102bf..e8eacdb47967 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h @@ -304,7 +304,7 @@ static const struct dpu_wb_cfg sc8180x_wb[] = { { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, - .features = WB_SDM845_MASK, + .features = WB_SM8250_MASK, .format_list = wb2_formats_rgb, .num_formats = ARRAY_SIZE(wb2_formats_rgb), .clk_ctrl = DPU_CLK_CTRL_WB2, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h index 621a2140f675..d761ed705bac 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h @@ -116,14 +116,12 @@ static const struct dpu_lm_cfg sm6150_lm[] = { .sblk = &sdm845_lm_sblk, .pingpong = PINGPONG_0, .dspp = DSPP_0, - .lm_pair = LM_1, }, { .name = "lm_1", .id = LM_1, .base = 0x45000, .len = 0x320, .features = MIXER_QCM2290_MASK, .sblk = &sdm845_lm_sblk, .pingpong = PINGPONG_1, - .lm_pair = LM_0, }, { .name = "lm_2", .id = LM_2, .base = 0x46000, .len = 0x320, diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h index d039b96beb97..76f60a2df7a8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h +++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h @@ -144,7 +144,7 @@ static const struct dpu_wb_cfg sm6125_wb[] = { { .name = "wb_2", .id = WB_2, .base = 0x65000, .len = 0x2c8, - .features = WB_SDM845_MASK, + .features = WB_SM8250_MASK, .format_list = wb2_formats_rgb, .num_formats = ARRAY_SIZE(wb2_formats_rgb), .clk_ctrl = DPU_CLK_CTRL_WB2, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 7191b1a6d41b..e5dcd41a361f 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1228,8 +1228,6 @@ static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state done: kfree(states); return ret; - - return 0; } static int dpu_crtc_atomic_check(struct drm_crtc *crtc, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 5172ab4dea99..48e6e8d74c85 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -2281,6 +2281,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) } } + if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither) + phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL); + /* reset the merge 3D HW block */ if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) { phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c index 657200401f57..cec6d4e8baec 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c @@ -52,6 +52,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, u32 slice_last_group_size; u32 det_thresh_flatness; bool is_cmd_mode = !(mode & DSC_MODE_VIDEO); + bool input_10_bits = dsc->bits_per_component == 10; DPU_REG_WRITE(c, DSC_COMMON_MODE, mode); @@ -68,7 +69,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, data |= (dsc->line_buf_depth << 3); data |= (dsc->simple_422 << 2); data |= (dsc->convert_rgb << 1); - data |= dsc->bits_per_component; + data |= input_10_bits; DPU_REG_WRITE(c, DSC_ENC, data); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c index ad19330de61a..562a3f4c5238 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c @@ -272,7 +272,7 @@ static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops, if (cap & BIT(DPU_MDP_VSYNC_SEL)) ops->setup_vsync_source = dpu_hw_setup_vsync_sel; - else + else if (!(cap & BIT(DPU_MDP_PERIPH_0_REMOVED))) ops->setup_vsync_source = dpu_hw_setup_wd_timer; ops->get_safe_status = dpu_hw_get_safe_status; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 098abc2c0003..af3e541f60c3 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -1164,7 +1164,6 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, unsigned int num_planes) { unsigned int i; - int ret; for (i = 0; i < num_planes; i++) { struct drm_plane_state *plane_state = states[i]; @@ -1173,13 +1172,13 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state, !plane_state->visible) continue; - ret = dpu_plane_virtual_assign_resources(crtc, global_state, + int ret = dpu_plane_virtual_assign_resources(crtc, global_state, state, plane_state); if (ret) - break; + return ret; } - return ret; + return 0; } static void dpu_plane_flush_csc(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe) diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c index 24dd37f1682b..3898850739ab 100644 --- a/drivers/gpu/drm/msm/dp/dp_display.c +++ b/drivers/gpu/drm/msm/dp/dp_display.c @@ -930,16 +930,17 @@ enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge, return -EINVAL; } - if (mode->clock > DP_MAX_PIXEL_CLK_KHZ) - return MODE_CLOCK_HIGH; - msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display); link_info = &msm_dp_display->panel->link_info; - if (drm_mode_is_420_only(&dp->connector->display_info, mode) && - msm_dp_display->panel->vsc_sdp_supported) + if ((drm_mode_is_420_only(&dp->connector->display_info, mode) && + msm_dp_display->panel->vsc_sdp_supported) || + msm_dp_wide_bus_available(dp)) mode_pclk_khz /= 2; + if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ) + return MODE_CLOCK_HIGH; + mode_bpp = dp->connector->display_info.bpc * num_components; if (!mode_bpp) mode_bpp = default_bpp; diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c index d3e241ea6941..16b7913d1eef 100644 --- a/drivers/gpu/drm/msm/dp/dp_drm.c +++ b/drivers/gpu/drm/msm/dp/dp_drm.c @@ -257,7 +257,10 @@ static enum drm_mode_status msm_edp_bridge_mode_valid(struct drm_bridge *bridge, return -EINVAL; } - if (mode->clock > DP_MAX_PIXEL_CLK_KHZ) + if (msm_dp_wide_bus_available(dp)) + mode_pclk_khz /= 2; + + if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ) return MODE_CLOCK_HIGH; /* diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 031446c87dae..798168180c1a 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -83,6 +83,9 @@ struct dsi_pll_7nm { /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */ spinlock_t postdiv_lock; + /* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */ + spinlock_t pclk_mux_lock; + struct pll_7nm_cached_state cached_state; struct dsi_pll_7nm *slave; @@ -372,22 +375,41 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll) ndelay(250); } -static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll) +static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val) { + unsigned long flags; + + spin_lock_irqsave(&pll->postdiv_lock, flags); + writel(val, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); + spin_unlock_irqrestore(&pll->postdiv_lock, flags); +} + +static void dsi_pll_cmn_clk_cfg1_update(struct dsi_pll_7nm *pll, u32 mask, + u32 val) +{ + unsigned long flags; u32 data; + spin_lock_irqsave(&pll->pclk_mux_lock, flags); data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + data &= ~mask; + data |= val & mask; + + writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + spin_unlock_irqrestore(&pll->pclk_mux_lock, flags); +} + +static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll) +{ + dsi_pll_cmn_clk_cfg1_update(pll, DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN, 0); } static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll) { - u32 data; + u32 cfg_1 = DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN | DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN_SEL; writel(0x04, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_3); - - data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - writel(data | BIT(5) | BIT(4), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + dsi_pll_cmn_clk_cfg1_update(pll, cfg_1, cfg_1); } static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll) @@ -565,7 +587,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) { struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw); struct pll_7nm_cached_state *cached = &pll_7nm->cached_state; - void __iomem *phy_base = pll_7nm->phy->base; u32 val; int ret; @@ -574,13 +595,10 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) val |= cached->pll_out_div; writel(val, pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); - writel(cached->bit_clk_div | (cached->pix_clk_div << 4), - phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); - - val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); - val &= ~0x3; - val |= cached->pll_mux; - writel(val, phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + dsi_pll_cmn_clk_cfg0_write(pll_7nm, + DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) | + DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div)); + dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux); ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw, pll_7nm->vco_current_rate, @@ -599,7 +617,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) { struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw); - void __iomem *base = phy->base; u32 data = 0x0; /* internal PLL */ DBG("DSI PLL%d", pll_7nm->phy->id); @@ -618,7 +635,8 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) } /* set PLL src */ - writel(data << 2, base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); + dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL__MASK, + DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL(data)); return 0; } @@ -733,7 +751,7 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide pll_by_2_bit, }), 2, 0, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, - 0, 1, 0, NULL); + 0, 1, 0, &pll_7nm->pclk_mux_lock); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; @@ -778,6 +796,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy) pll_7nm_list[phy->id] = pll_7nm; spin_lock_init(&pll_7nm->postdiv_lock); + spin_lock_init(&pll_7nm->pclk_mux_lock); pll_7nm->phy = phy; diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index fee31680a6d5..a65077855201 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -537,15 +537,12 @@ static inline int align_pitch(int width, int bpp) static inline unsigned long timeout_to_jiffies(const ktime_t *timeout) { ktime_t now = ktime_get(); - s64 remaining_jiffies; - if (ktime_compare(*timeout, now) < 0) { - remaining_jiffies = 0; - } else { - ktime_t rem = ktime_sub(*timeout, now); - remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ); - } + if (ktime_compare(*timeout, now) <= 0) + return 0; + ktime_t rem = ktime_sub(*timeout, now); + s64 remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ); return clamp(remaining_jiffies, 1LL, (s64)INT_MAX); } diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml index d54b72f92449..35f7f40e405b 100644 --- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml +++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml @@ -9,8 +9,15 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd"> <reg32 offset="0x00004" name="REVISION_ID1"/> <reg32 offset="0x00008" name="REVISION_ID2"/> <reg32 offset="0x0000c" name="REVISION_ID3"/> - <reg32 offset="0x00010" name="CLK_CFG0"/> - <reg32 offset="0x00014" name="CLK_CFG1"/> + <reg32 offset="0x00010" name="CLK_CFG0"> + <bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/> + <bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/> + </reg32> + <reg32 offset="0x00014" name="CLK_CFG1"> + <bitfield name="CLK_EN" pos="5" type="boolean"/> + <bitfield name="CLK_EN_SEL" pos="4" type="boolean"/> + <bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/> + </reg32> <reg32 offset="0x00018" name="GLBL_CTRL"/> <reg32 offset="0x0001c" name="RBUF_CTRL"/> <reg32 offset="0x00020" name="VREG_CTRL_0"/> diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index b4da82ddbb6b..8ea98f06d39a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -590,6 +590,7 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm, unsigned long timeout = jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT); struct mm_struct *mm = svmm->notifier.mm; + struct folio *folio; struct page *page; unsigned long start = args->p.addr; unsigned long notifier_seq; @@ -616,12 +617,16 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm, ret = -EINVAL; goto out; } + folio = page_folio(page); mutex_lock(&svmm->mutex); if (!mmu_interval_read_retry(¬ifier->notifier, notifier_seq)) break; mutex_unlock(&svmm->mutex); + + folio_unlock(folio); + folio_put(folio); } /* Map the page on the GPU. */ @@ -637,8 +642,8 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm, ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL); mutex_unlock(&svmm->mutex); - unlock_page(page); - put_page(page); + folio_unlock(folio); + folio_put(folio); out: mmu_interval_notifier_remove(¬ifier->notifier); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c index a6f410ba60bc..d393bc540f86 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c @@ -75,7 +75,7 @@ gp10b_pmu_acr = { .bootstrap_multiple_falcons = gp10b_pmu_acr_bootstrap_multiple_falcons, }; -#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC) +#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC) MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin"); MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin"); MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin"); diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c index 45d09e6fa667..7d68a8acfe2e 100644 --- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c +++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c @@ -109,13 +109,13 @@ static int jadard_prepare(struct drm_panel *panel) if (jadard->desc->lp11_to_reset_delay_ms) msleep(jadard->desc->lp11_to_reset_delay_ms); - gpiod_set_value(jadard->reset, 1); + gpiod_set_value(jadard->reset, 0); msleep(5); - gpiod_set_value(jadard->reset, 0); + gpiod_set_value(jadard->reset, 1); msleep(10); - gpiod_set_value(jadard->reset, 1); + gpiod_set_value(jadard->reset, 0); msleep(130); ret = jadard->desc->init(jadard); @@ -1130,7 +1130,7 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi) dsi->format = desc->format; dsi->lanes = desc->lanes; - jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(jadard->reset)) { DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n"); return PTR_ERR(jadard->reset); diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c index 50c8076b5158..72ad576fc18e 100644 --- a/drivers/gpu/drm/xe/xe_guc_ct.c +++ b/drivers/gpu/drm/xe/xe_guc_ct.c @@ -1723,9 +1723,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, drm_printf(p, "\tg2h outstanding: %d\n", snapshot->g2h_outstanding); - if (snapshot->ctb) - xe_print_blob_ascii85(p, "CTB data", '\n', + if (snapshot->ctb) { + drm_printf(p, "[CTB].length: 0x%zx\n", snapshot->ctb_size); + xe_print_blob_ascii85(p, "[CTB].data", '\n', snapshot->ctb, 0, snapshot->ctb_size); + } } else { drm_puts(p, "CT disabled\n"); } diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c index 2baa4d95571f..0ca3056d8bd3 100644 --- a/drivers/gpu/drm/xe/xe_guc_log.c +++ b/drivers/gpu/drm/xe/xe_guc_log.c @@ -208,10 +208,11 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_ drm_printf(p, "GuC timestamp: 0x%08llX [%llu]\n", snapshot->stamp, snapshot->stamp); drm_printf(p, "Log level: %u\n", snapshot->level); + drm_printf(p, "[LOG].length: 0x%zx\n", snapshot->size); remain = snapshot->size; for (i = 0; i < snapshot->num_chunks; i++) { size_t size = min(GUC_LOG_CHUNK_SIZE, remain); - const char *prefix = i ? NULL : "Log data"; + const char *prefix = i ? NULL : "[LOG].data"; char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0; xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size); diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c index 32f5a67a917b..08552ee3fb94 100644 --- a/drivers/gpu/drm/xe/xe_irq.c +++ b/drivers/gpu/drm/xe/xe_irq.c @@ -757,19 +757,7 @@ int xe_irq_install(struct xe_device *xe) xe_irq_postinstall(xe); - err = devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe); - if (err) - goto free_irq_handler; - - return 0; - -free_irq_handler: - if (xe_device_has_msix(xe)) - xe_irq_msix_free(xe); - else - xe_irq_msi_free(xe); - - return err; + return devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe); } static void xe_irq_msi_synchronize_irq(struct xe_device *xe) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 76dce0aac246..270d7a4d85a6 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -44,6 +44,7 @@ static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI; #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 2) +#define FLAGS_WORKAROUND_INSECURE (1ULL << 3) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) @@ -83,6 +84,8 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) +static bool nmi_support_forbidden; + /* * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs * are potentially stolen by the secure side. Some code, especially code dealing @@ -163,21 +166,27 @@ static void __init gic_prio_init(void) { bool ds; - ds = gic_dist_security_disabled(); - if (!ds) { - u32 val; - - val = readl_relaxed(gic_data.dist_base + GICD_CTLR); - val |= GICD_CTLR_DS; - writel_relaxed(val, gic_data.dist_base + GICD_CTLR); + cpus_have_group0 = gic_has_group0(); - ds = gic_dist_security_disabled(); - if (ds) - pr_warn("Broken GIC integration, security disabled"); + ds = gic_dist_security_disabled(); + if ((gic_data.flags & FLAGS_WORKAROUND_INSECURE) && !ds) { + if (cpus_have_group0) { + u32 val; + + val = readl_relaxed(gic_data.dist_base + GICD_CTLR); + val |= GICD_CTLR_DS; + writel_relaxed(val, gic_data.dist_base + GICD_CTLR); + + ds = gic_dist_security_disabled(); + if (ds) + pr_warn("Broken GIC integration, security disabled\n"); + } else { + pr_warn("Broken GIC integration, pNMI forbidden\n"); + nmi_support_forbidden = true; + } } cpus_have_security_disabled = ds; - cpus_have_group0 = gic_has_group0(); /* * How priority values are used by the GIC depends on two things: @@ -209,7 +218,7 @@ static void __init gic_prio_init(void) * be in the non-secure range, we program the non-secure values into * the distributor to match the PMR values we want. */ - if (cpus_have_group0 & !cpus_have_security_disabled) { + if (cpus_have_group0 && !cpus_have_security_disabled) { dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq); dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi); } @@ -1922,6 +1931,18 @@ static bool gic_enable_quirk_arm64_2941627(void *data) return true; } +static bool gic_enable_quirk_rk3399(void *data) +{ + struct gic_chip_data *d = data; + + if (of_machine_is_compatible("rockchip,rk3399")) { + d->flags |= FLAGS_WORKAROUND_INSECURE; + return true; + } + + return false; +} + static bool rd_set_non_coherent(void *data) { struct gic_chip_data *d = data; @@ -1997,6 +2018,12 @@ static const struct gic_quirk gic_quirks[] = { .init = rd_set_non_coherent, }, { + .desc = "GICv3: Insecure RK3399 integration", + .iidr = 0x0000043b, + .mask = 0xff000fff, + .init = gic_enable_quirk_rk3399, + }, + { } }; @@ -2004,7 +2031,7 @@ static void gic_enable_nmi_support(void) { int i; - if (!gic_prio_masking_enabled()) + if (!gic_prio_masking_enabled() || nmi_support_forbidden) return; rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR, diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c index b9dcc8e78c75..1f613eb7b7f0 100644 --- a/drivers/irqchip/irq-jcore-aic.c +++ b/drivers/irqchip/irq-jcore-aic.c @@ -38,7 +38,7 @@ static struct irq_chip jcore_aic; static void handle_jcore_irq(struct irq_desc *desc) { if (irqd_is_per_cpu(irq_desc_get_irq_data(desc))) - handle_percpu_irq(desc); + handle_percpu_devid_irq(desc); else handle_simple_irq(desc); } diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c index 74b2f124116e..52d77546aacb 100644 --- a/drivers/irqchip/qcom-pdc.c +++ b/drivers/irqchip/qcom-pdc.c @@ -21,9 +21,11 @@ #include <linux/types.h> #define PDC_MAX_GPIO_IRQS 256 +#define PDC_DRV_OFFSET 0x10000 /* Valid only on HW version < 3.2 */ #define IRQ_ENABLE_BANK 0x10 +#define IRQ_ENABLE_BANK_MAX (IRQ_ENABLE_BANK + BITS_TO_BYTES(PDC_MAX_GPIO_IRQS)) #define IRQ_i_CFG 0x110 /* Valid only on HW version >= 3.2 */ @@ -46,13 +48,20 @@ struct pdc_pin_region { static DEFINE_RAW_SPINLOCK(pdc_lock); static void __iomem *pdc_base; +static void __iomem *pdc_prev_base; static struct pdc_pin_region *pdc_region; static int pdc_region_cnt; static unsigned int pdc_version; +static bool pdc_x1e_quirk; + +static void pdc_base_reg_write(void __iomem *base, int reg, u32 i, u32 val) +{ + writel_relaxed(val, base + reg + i * sizeof(u32)); +} static void pdc_reg_write(int reg, u32 i, u32 val) { - writel_relaxed(val, pdc_base + reg + i * sizeof(u32)); + pdc_base_reg_write(pdc_base, reg, i, val); } static u32 pdc_reg_read(int reg, u32 i) @@ -60,6 +69,34 @@ static u32 pdc_reg_read(int reg, u32 i) return readl_relaxed(pdc_base + reg + i * sizeof(u32)); } +static void pdc_x1e_irq_enable_write(u32 bank, u32 enable) +{ + void __iomem *base; + + /* Remap the write access to work around a hardware bug on X1E */ + switch (bank) { + case 0 ... 1: + /* Use previous DRV (client) region and shift to bank 3-4 */ + base = pdc_prev_base; + bank += 3; + break; + case 2 ... 4: + /* Use our own region and shift to bank 0-2 */ + base = pdc_base; + bank -= 2; + break; + case 5: + /* No fixup required for bank 5 */ + base = pdc_base; + break; + default: + WARN_ON(1); + return; + } + + pdc_base_reg_write(base, IRQ_ENABLE_BANK, bank, enable); +} + static void __pdc_enable_intr(int pin_out, bool on) { unsigned long enable; @@ -72,7 +109,11 @@ static void __pdc_enable_intr(int pin_out, bool on) enable = pdc_reg_read(IRQ_ENABLE_BANK, index); __assign_bit(mask, &enable, on); - pdc_reg_write(IRQ_ENABLE_BANK, index, enable); + + if (pdc_x1e_quirk) + pdc_x1e_irq_enable_write(index, enable); + else + pdc_reg_write(IRQ_ENABLE_BANK, index, enable); } else { enable = pdc_reg_read(IRQ_i_CFG, pin_out); __assign_bit(IRQ_i_CFG_IRQ_ENABLE, &enable, on); @@ -324,10 +365,29 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent) if (res_size > resource_size(&res)) pr_warn("%pOF: invalid reg size, please fix DT\n", node); + /* + * PDC has multiple DRV regions, each one provides the same set of + * registers for a particular client in the system. Due to a hardware + * bug on X1E, some writes to the IRQ_ENABLE_BANK register must be + * issued inside the previous region. This region belongs to + * a different client and is not described in the device tree. Map the + * region with the expected offset to preserve support for old DTs. + */ + if (of_device_is_compatible(node, "qcom,x1e80100-pdc")) { + pdc_prev_base = ioremap(res.start - PDC_DRV_OFFSET, IRQ_ENABLE_BANK_MAX); + if (!pdc_prev_base) { + pr_err("%pOF: unable to map previous PDC DRV region\n", node); + return -ENXIO; + } + + pdc_x1e_quirk = true; + } + pdc_base = ioremap(res.start, res_size); if (!pdc_base) { pr_err("%pOF: unable to map PDC registers\n", node); - return -ENXIO; + ret = -ENXIO; + goto fail; } pdc_version = pdc_reg_read(PDC_VERSION_REG, 0); @@ -363,6 +423,7 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent) fail: kfree(pdc_region); iounmap(pdc_base); + iounmap(pdc_prev_base); return ret; } diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index 8fc9339b00c7..70bcc3cdf2cd 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -386,10 +386,8 @@ static int raid0_set_limits(struct mddev *mddev) lim.io_opt = lim.io_min * mddev->raid_disks; lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 9d57a88dbd26..10ea3af40991 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -3219,10 +3219,8 @@ static int raid1_set_limits(struct mddev *mddev) lim.max_write_zeroes_sectors = 0; lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index efe93b979167..15b9ae5bf84d 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4020,10 +4020,8 @@ static int raid10_set_queue_limits(struct mddev *mddev) lim.io_opt = lim.io_min * raid10_nr_stripes(conf); lim.features |= BLK_FEAT_ATOMIC_WRITES; err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY); - if (err) { - queue_limits_cancel_update(mddev->gendisk->queue); + if (err) return err; - } return queue_limits_set(mddev->gendisk->queue, &lim); } diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c index 8d1d710e439d..6667eea95597 100644 --- a/drivers/mtd/nand/raw/cadence-nand-controller.c +++ b/drivers/mtd/nand/raw/cadence-nand-controller.c @@ -471,6 +471,8 @@ struct cdns_nand_ctrl { struct { void __iomem *virt; dma_addr_t dma; + dma_addr_t iova_dma; + u32 size; } io; int irq; @@ -1835,11 +1837,11 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl, } if (dir == DMA_FROM_DEVICE) { - src_dma = cdns_ctrl->io.dma; + src_dma = cdns_ctrl->io.iova_dma; dst_dma = buf_dma; } else { src_dma = buf_dma; - dst_dma = cdns_ctrl->io.dma; + dst_dma = cdns_ctrl->io.iova_dma; } tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len, @@ -1861,12 +1863,12 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl, dma_async_issue_pending(cdns_ctrl->dmac); wait_for_completion(&finished); - dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir); + dma_unmap_single(dma_dev->dev, buf_dma, len, dir); return 0; err_unmap: - dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir); + dma_unmap_single(dma_dev->dev, buf_dma, len, dir); err: dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n"); @@ -2869,6 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl) static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) { dma_cap_mask_t mask; + struct dma_device *dma_dev = cdns_ctrl->dmac->device; int ret; cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev, @@ -2904,15 +2907,24 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) dma_cap_set(DMA_MEMCPY, mask); if (cdns_ctrl->caps1->has_dma) { - cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL); - if (!cdns_ctrl->dmac) { - dev_err(cdns_ctrl->dev, - "Unable to get a DMA channel\n"); - ret = -EBUSY; + cdns_ctrl->dmac = dma_request_chan_by_mask(&mask); + if (IS_ERR(cdns_ctrl->dmac)) { + ret = dev_err_probe(cdns_ctrl->dev, PTR_ERR(cdns_ctrl->dmac), + "%d: Failed to get a DMA channel\n", ret); goto disable_irq; } } + cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma, + cdns_ctrl->io.size, + DMA_BIDIRECTIONAL, 0); + + ret = dma_mapping_error(dma_dev->dev, cdns_ctrl->io.iova_dma); + if (ret) { + dev_err(cdns_ctrl->dev, "Failed to map I/O resource to DMA\n"); + goto dma_release_chnl; + } + nand_controller_init(&cdns_ctrl->controller); INIT_LIST_HEAD(&cdns_ctrl->chips); @@ -2923,18 +2935,22 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl) if (ret) { dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n", ret); - goto dma_release_chnl; + goto unmap_dma_resource; } kfree(cdns_ctrl->buf); cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL); if (!cdns_ctrl->buf) { ret = -ENOMEM; - goto dma_release_chnl; + goto unmap_dma_resource; } return 0; +unmap_dma_resource: + dma_unmap_resource(dma_dev->dev, cdns_ctrl->io.iova_dma, + cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0); + dma_release_chnl: if (cdns_ctrl->dmac) dma_release_channel(cdns_ctrl->dmac); @@ -2956,6 +2972,10 @@ free_buf_desc: static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl) { cadence_nand_chips_cleanup(cdns_ctrl); + if (cdns_ctrl->dmac) + dma_unmap_resource(cdns_ctrl->dmac->device->dev, + cdns_ctrl->io.iova_dma, cdns_ctrl->io.size, + DMA_BIDIRECTIONAL, 0); cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl); kfree(cdns_ctrl->buf); dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc), @@ -3020,7 +3040,9 @@ static int cadence_nand_dt_probe(struct platform_device *ofdev) cdns_ctrl->io.virt = devm_platform_get_and_ioremap_resource(ofdev, 1, &res); if (IS_ERR(cdns_ctrl->io.virt)) return PTR_ERR(cdns_ctrl->io.virt); + cdns_ctrl->io.dma = res->start; + cdns_ctrl->io.size = resource_size(res); dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk"); if (IS_ERR(dt->clk)) diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index d2d2aeee42a7..6720b547892b 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -1881,18 +1881,18 @@ static int qcom_param_page_type_exec(struct nand_chip *chip, const struct nand_ nandc->regs->addr0 = 0; nandc->regs->addr1 = 0; - host->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, 0) | - FIELD_PREP(UD_SIZE_BYTES_MASK, 512) | - FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) | - FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0); - - host->cfg1 = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) | - FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) | - FIELD_PREP(CS_ACTIVE_BSY, 0) | - FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) | - FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) | - FIELD_PREP(WIDE_FLASH, 0) | - FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1); + nandc->regs->cfg0 = cpu_to_le32(FIELD_PREP(CW_PER_PAGE_MASK, 0) | + FIELD_PREP(UD_SIZE_BYTES_MASK, 512) | + FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) | + FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0)); + + nandc->regs->cfg1 = cpu_to_le32(FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) | + FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) | + FIELD_PREP(CS_ACTIVE_BSY, 0) | + FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) | + FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) | + FIELD_PREP(WIDE_FLASH, 0) | + FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1)); if (!nandc->props->qpic_version2) nandc->regs->ecc_buf_cfg = cpu_to_le32(ECC_CFG_ECC_DISABLE); diff --git a/drivers/mtd/spi-nor/sst.c b/drivers/mtd/spi-nor/sst.c index b5ad7118c49a..175211fe6a5e 100644 --- a/drivers/mtd/spi-nor/sst.c +++ b/drivers/mtd/spi-nor/sst.c @@ -174,7 +174,7 @@ static int sst_nor_write_data(struct spi_nor *nor, loff_t to, size_t len, int ret; nor->program_opcode = op; - ret = spi_nor_write_data(nor, to, 1, buf); + ret = spi_nor_write_data(nor, to, len, buf); if (ret < 0) return ret; WARN(ret != len, "While writing %zu byte written %i bytes\n", len, ret); diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 8167cc5fb0df..78d2a19593d1 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -1116,6 +1116,16 @@ static inline u32 gve_xdp_tx_start_queue_id(struct gve_priv *priv) return gve_xdp_tx_queue_id(priv, 0); } +static inline bool gve_supports_xdp_xmit(struct gve_priv *priv) +{ + switch (priv->queue_format) { + case GVE_GQI_QPL_FORMAT: + return true; + default: + return false; + } +} + /* gqi napi handler defined in gve_main.c */ int gve_napi_poll(struct napi_struct *napi, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 533e659b15b3..92237fb0b60c 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1903,6 +1903,8 @@ static void gve_turndown(struct gve_priv *priv) /* Stop tx queues */ netif_tx_disable(priv->dev); + xdp_features_clear_redirect_target(priv->dev); + gve_clear_napi_enabled(priv); gve_clear_report_stats(priv); @@ -1972,6 +1974,9 @@ static void gve_turnup(struct gve_priv *priv) napi_schedule(&block->napi); } + if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv)) + xdp_features_set_redirect_target(priv->dev, false); + gve_set_napi_enabled(priv); } @@ -2246,7 +2251,6 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) if (priv->queue_format == GVE_GQI_QPL_FORMAT) { xdp_features = NETDEV_XDP_ACT_BASIC; xdp_features |= NETDEV_XDP_ACT_REDIRECT; - xdp_features |= NETDEV_XDP_ACT_NDO_XMIT; xdp_features |= NETDEV_XDP_ACT_XSK_ZEROCOPY; } else { xdp_features = 0; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index e95ae0d39948..0676fc547b6f 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -2408,6 +2408,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) dma_addr_t data_dma_addr; struct netdev_queue *txq; unsigned long lpar_rc; + unsigned int skblen; union sub_crq tx_crq; unsigned int offset; bool use_scrq_send_direct = false; @@ -2522,6 +2523,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) tx_buff->skb = skb; tx_buff->index = bufidx; tx_buff->pool_index = queue_num; + skblen = skb->len; memset(&tx_crq, 0, sizeof(tx_crq)); tx_crq.v1.first = IBMVNIC_CRQ_CMD; @@ -2614,7 +2616,7 @@ early_exit: netif_stop_subqueue(netdev, queue_num); } - tx_bytes += skb->len; + tx_bytes += skblen; txq_trans_cond_update(txq); ret = NETDEV_TX_OK; goto out; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 2ec62c8d86e1..59486fe2ad18 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -20,6 +20,8 @@ nfp_bpf_cmsg_alloc(struct nfp_app_bpf *bpf, unsigned int size) struct sk_buff *skb; skb = nfp_app_ctrl_msg_alloc(bpf->app, size, GFP_KERNEL); + if (!skb) + return NULL; skb_put(skb, size); return skb; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9e7fa012e4fa..f33178f90c42 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -2897,6 +2897,7 @@ static int axienet_probe(struct platform_device *pdev) lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; + lp->phylink_config.mac_managed_pm = true; lp->phylink_config.mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10FD | MAC_100FD | MAC_1000FD; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 642155cb8315..dbb3960126ee 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1902,21 +1902,9 @@ static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; - struct net_device *dev, *aux; - /* gather any geneve devices that were moved into this ns */ - for_each_netdev_safe(net, dev, aux) - if (dev->rtnl_link_ops == &geneve_link_ops) - unregister_netdevice_queue(dev, head); - - /* now gather any other geneve devices that were created in this ns */ - list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { - /* If geneve->dev is in the same netns, it was already added - * to the list by the previous loop. - */ - if (!net_eq(dev_net(geneve->dev), net)) - unregister_netdevice_queue(geneve->dev, head); - } + list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) + geneve_dellink(geneve->dev, head); } static void __net_exit geneve_exit_batch_rtnl(struct list_head *net_list, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index d64740bf44ed..b7b46c5e6399 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -2481,11 +2481,6 @@ static void __net_exit gtp_net_exit_batch_rtnl(struct list_head *net_list, list_for_each_entry(net, net_list, exit_list) { struct gtp_net *gn = net_generic(net, gtp_net_id); struct gtp_dev *gtp, *gtp_next; - struct net_device *dev; - - for_each_netdev(net, dev) - if (dev->rtnl_link_ops == >p_link_ops) - gtp_dellink(dev, dev_to_kill); list_for_each_entry_safe(gtp, gtp_next, &gn->gtp_dev_list, list) gtp_dellink(gtp->dev, dev_to_kill); diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index fc9e23927b3b..7d60a714ca53 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -1047,7 +1047,7 @@ static int pd692x0_pi_get_pw_limit(struct pse_controller_dev *pcdev, if (ret < 0) return ret; - return pd692x0_pi_get_pw_from_table(buf.data[2], buf.data[3]); + return pd692x0_pi_get_pw_from_table(buf.data[0], buf.data[1]); } static int pd692x0_pi_set_pw_limit(struct pse_controller_dev *pcdev, diff --git a/drivers/net/wwan/mhi_wwan_mbim.c b/drivers/net/wwan/mhi_wwan_mbim.c index d5a9360323d2..8755c5e6a65b 100644 --- a/drivers/net/wwan/mhi_wwan_mbim.c +++ b/drivers/net/wwan/mhi_wwan_mbim.c @@ -220,7 +220,7 @@ static int mbim_rx_verify_nth16(struct mhi_mbim_context *mbim, struct sk_buff *s if (mbim->rx_seq + 1 != le16_to_cpu(nth16->wSequence) && (mbim->rx_seq || le16_to_cpu(nth16->wSequence)) && !(mbim->rx_seq == 0xffff && !le16_to_cpu(nth16->wSequence))) { - net_err_ratelimited("sequence number glitch prev=%d curr=%d\n", + net_dbg_ratelimited("sequence number glitch prev=%d curr=%d\n", mbim->rx_seq, le16_to_cpu(nth16->wSequence)); } mbim->rx_seq = le16_to_cpu(nth16->wSequence); diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c index 1de11b722f04..a060f69558e7 100644 --- a/drivers/nvme/host/apple.c +++ b/drivers/nvme/host/apple.c @@ -1011,25 +1011,37 @@ static void apple_nvme_reset_work(struct work_struct *work) ret = apple_rtkit_shutdown(anv->rtk); if (ret) goto out; + + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); } - writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + /* + * Only do the soft-reset if the CPU is not running, which means either we + * or the previous stage shut it down cleanly. + */ + if (!(readl(anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL) & + APPLE_ANS_COPROC_CPU_CONTROL_RUN)) { - ret = reset_control_assert(anv->reset); - if (ret) - goto out; + ret = reset_control_assert(anv->reset); + if (ret) + goto out; - ret = apple_rtkit_reinit(anv->rtk); - if (ret) - goto out; + ret = apple_rtkit_reinit(anv->rtk); + if (ret) + goto out; - ret = reset_control_deassert(anv->reset); - if (ret) - goto out; + ret = reset_control_deassert(anv->reset); + if (ret) + goto out; + + writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN, + anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + + ret = apple_rtkit_boot(anv->rtk); + } else { + ret = apple_rtkit_wake(anv->rtk); + } - writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN, - anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); - ret = apple_rtkit_boot(anv->rtk); if (ret) { dev_err(anv->dev, "ANS did not boot"); goto out; @@ -1516,6 +1528,7 @@ static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev) return anv; put_dev: + apple_nvme_detach_genpd(anv); put_device(anv->dev); return ERR_PTR(ret); } @@ -1549,6 +1562,7 @@ out_uninit_ctrl: nvme_uninit_ctrl(&anv->ctrl); out_put_ctrl: nvme_put_ctrl(&anv->ctrl); + apple_nvme_detach_genpd(anv); return ret; } @@ -1563,9 +1577,12 @@ static void apple_nvme_remove(struct platform_device *pdev) apple_nvme_disable(anv, true); nvme_uninit_ctrl(&anv->ctrl); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { apple_rtkit_shutdown(anv->rtk); + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } + apple_nvme_detach_genpd(anv); } @@ -1574,8 +1591,11 @@ static void apple_nvme_shutdown(struct platform_device *pdev) struct apple_nvme *anv = platform_get_drvdata(pdev); apple_nvme_disable(anv, true); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { apple_rtkit_shutdown(anv->rtk); + + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } } static int apple_nvme_resume(struct device *dev) @@ -1592,10 +1612,11 @@ static int apple_nvme_suspend(struct device *dev) apple_nvme_disable(anv, true); - if (apple_rtkit_is_running(anv->rtk)) + if (apple_rtkit_is_running(anv->rtk)) { ret = apple_rtkit_shutdown(anv->rtk); - writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL); + } return ret; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 818d4e49aab5..f028913e2e62 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -564,8 +564,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl, switch (new_state) { case NVME_CTRL_LIVE: switch (old_state) { - case NVME_CTRL_NEW: - case NVME_CTRL_RESETTING: case NVME_CTRL_CONNECTING: changed = true; fallthrough; diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index f4f1866fbd5b..b9929a5a7f4e 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -781,61 +781,12 @@ restart: static void nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl) { - enum nvme_ctrl_state state; - unsigned long flags; - dev_info(ctrl->ctrl.device, "NVME-FC{%d}: controller connectivity lost. Awaiting " "Reconnect", ctrl->cnum); - spin_lock_irqsave(&ctrl->lock, flags); set_bit(ASSOC_FAILED, &ctrl->flags); - state = nvme_ctrl_state(&ctrl->ctrl); - spin_unlock_irqrestore(&ctrl->lock, flags); - - switch (state) { - case NVME_CTRL_NEW: - case NVME_CTRL_LIVE: - /* - * Schedule a controller reset. The reset will terminate the - * association and schedule the reconnect timer. Reconnects - * will be attempted until either the ctlr_loss_tmo - * (max_retries * connect_delay) expires or the remoteport's - * dev_loss_tmo expires. - */ - if (nvme_reset_ctrl(&ctrl->ctrl)) { - dev_warn(ctrl->ctrl.device, - "NVME-FC{%d}: Couldn't schedule reset.\n", - ctrl->cnum); - nvme_delete_ctrl(&ctrl->ctrl); - } - break; - - case NVME_CTRL_CONNECTING: - /* - * The association has already been terminated and the - * controller is attempting reconnects. No need to do anything - * futher. Reconnects will be attempted until either the - * ctlr_loss_tmo (max_retries * connect_delay) expires or the - * remoteport's dev_loss_tmo expires. - */ - break; - - case NVME_CTRL_RESETTING: - /* - * Controller is already in the process of terminating the - * association. No need to do anything further. The reconnect - * step will kick in naturally after the association is - * terminated. - */ - break; - - case NVME_CTRL_DELETING: - case NVME_CTRL_DELETING_NOIO: - default: - /* no action to take - let it delete */ - break; - } + nvme_reset_ctrl(&ctrl->ctrl); } /** @@ -3071,7 +3022,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) struct nvmefc_ls_rcv_op *disls = NULL; unsigned long flags; int ret; - bool changed; ++ctrl->ctrl.nr_reconnects; @@ -3177,23 +3127,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } + if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) + ret = -EIO; if (ret) goto out_term_aen_ops; - spin_lock_irqsave(&ctrl->lock, flags); - if (!test_bit(ASSOC_FAILED, &ctrl->flags)) - changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); - else + if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) { ret = -EIO; - spin_unlock_irqrestore(&ctrl->lock, flags); - - if (ret) goto out_term_aen_ops; + } ctrl->ctrl.nr_reconnects = 0; - - if (changed) - nvme_start_ctrl(&ctrl->ctrl); + nvme_start_ctrl(&ctrl->ctrl); return 0; /* Success */ diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index e8930146847a..b1b46c2713e1 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -283,8 +283,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl, { if (ns && nsid != ns->head->ns_id) { dev_err(ctrl->device, - "%s: nsid (%u) in cmd does not match nsid (%u)" - "of namespace\n", + "%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n", current->comm, nsid, ns->head->ns_id); return false; } diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9197a5b173fd..950289405ef2 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3706,6 +3706,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc1, 0x5350), /* ADATA XPG GAMMIX S50 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, + { PCI_DEVICE(0x1dbe, 0x5216), /* Acer/INNOGRIT FA100/5216 NVMe SSD */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1dbe, 0x5236), /* ADATA XPG GAMMIX S70 */ .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1e49, 0x0021), /* ZHITAI TiPro5000 NVMe SSD */ diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 841238f38fdd..8a9131c95a3d 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -763,6 +763,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue, return 0; } +static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue, + struct nvme_tcp_term_pdu *pdu) +{ + u16 fes; + const char *msg; + u32 plen = le32_to_cpu(pdu->hdr.plen); + + static const char * const msg_table[] = { + [NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field", + [NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error", + [NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error", + [NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range", + [NVME_TCP_FES_R2T_LIMIT_EXCEEDED] = "R2T Limit Exceeded", + [NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter", + }; + + if (plen < NVME_TCP_MIN_C2HTERM_PLEN || + plen > NVME_TCP_MAX_C2HTERM_PLEN) { + dev_err(queue->ctrl->ctrl.device, + "Received a malformed C2HTermReq PDU (plen = %u)\n", + plen); + return; + } + + fes = le16_to_cpu(pdu->fes); + if (fes && fes < ARRAY_SIZE(msg_table)) + msg = msg_table[fes]; + else + msg = "Unknown"; + + dev_err(queue->ctrl->ctrl.device, + "Received C2HTermReq (FES = %s)\n", msg); +} + static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, unsigned int *offset, size_t *len) { @@ -784,6 +818,15 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb, return 0; hdr = queue->pdu; + if (unlikely(hdr->type == nvme_tcp_c2h_term)) { + /* + * C2HTermReq never includes Header or Data digests. + * Skip the checks. + */ + nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu); + return -EINVAL; + } + if (queue->hdr_digest) { ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen); if (unlikely(ret)) @@ -1449,11 +1492,14 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue) msg.msg_control = cbuf; msg.msg_controllen = sizeof(cbuf); } + msg.msg_flags = MSG_WAITALL; ret = kernel_recvmsg(queue->sock, &msg, &iov, 1, iov.iov_len, msg.msg_flags); - if (ret < 0) { + if (ret < sizeof(*icresp)) { pr_warn("queue %d: failed to receive icresp, error %d\n", nvme_tcp_queue_id(queue), ret); + if (ret >= 0) + ret = -ECONNRESET; goto free_icresp; } ret = -ENOTCONN; @@ -1565,7 +1611,7 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue) ctrl->io_queues[HCTX_TYPE_POLL]; } -/** +/* * Track the number of queues assigned to each cpu using a global per-cpu * counter and select the least used cpu from the mq_map. Our goal is to spread * different controllers I/O threads across different cpu cores. diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index cdc4a09a6e8a..2e741696f371 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -606,6 +606,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns) goto out_dev_put; } + if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL)) + goto out_pr_exit; + nvmet_ns_changed(subsys, ns->nsid); ns->enabled = true; xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED); @@ -613,6 +616,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns) out_unlock: mutex_unlock(&subsys->lock); return ret; +out_pr_exit: + if (ns->pr.enable) + nvmet_pr_exit_ns(ns); out_dev_put: list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid)); @@ -638,6 +644,19 @@ void nvmet_ns_disable(struct nvmet_ns *ns) mutex_unlock(&subsys->lock); + /* + * Now that we removed the namespaces from the lookup list, we + * can kill the per_cpu ref and wait for any remaining references + * to be dropped, as well as a RCU grace period for anyone only + * using the namepace under rcu_read_lock(). Note that we can't + * use call_rcu here as we need to ensure the namespaces have + * been fully destroyed before unloading the module. + */ + percpu_ref_kill(&ns->ref); + synchronize_rcu(); + wait_for_completion(&ns->disable_done); + percpu_ref_exit(&ns->ref); + if (ns->pr.enable) nvmet_pr_exit_ns(ns); @@ -660,22 +679,6 @@ void nvmet_ns_free(struct nvmet_ns *ns) if (ns->nsid == subsys->max_nsid) subsys->max_nsid = nvmet_max_nsid(subsys); - mutex_unlock(&subsys->lock); - - /* - * Now that we removed the namespaces from the lookup list, we - * can kill the per_cpu ref and wait for any remaining references - * to be dropped, as well as a RCU grace period for anyone only - * using the namepace under rcu_read_lock(). Note that we can't - * use call_rcu here as we need to ensure the namespaces have - * been fully destroyed before unloading the module. - */ - percpu_ref_kill(&ns->ref); - synchronize_rcu(); - wait_for_completion(&ns->disable_done); - percpu_ref_exit(&ns->ref); - - mutex_lock(&subsys->lock); subsys->nr_namespaces--; mutex_unlock(&subsys->lock); @@ -705,9 +708,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) ns->nsid = nsid; ns->subsys = subsys; - if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL)) - goto out_free; - if (ns->nsid > subsys->max_nsid) subsys->max_nsid = nsid; @@ -730,8 +730,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid) return ns; out_exit: subsys->max_nsid = nvmet_max_nsid(subsys); - percpu_ref_exit(&ns->ref); -out_free: kfree(ns); out_unlock: mutex_unlock(&subsys->lock); diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 4be8d22d2d8d..d2c1233981e1 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -784,37 +784,37 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req); static inline bool nvmet_cc_en(u32 cc) { - return (cc >> NVME_CC_EN_SHIFT) & 0x1; + return (cc & NVME_CC_ENABLE) >> NVME_CC_EN_SHIFT; } static inline u8 nvmet_cc_css(u32 cc) { - return (cc >> NVME_CC_CSS_SHIFT) & 0x7; + return (cc & NVME_CC_CSS_MASK) >> NVME_CC_CSS_SHIFT; } static inline u8 nvmet_cc_mps(u32 cc) { - return (cc >> NVME_CC_MPS_SHIFT) & 0xf; + return (cc & NVME_CC_MPS_MASK) >> NVME_CC_MPS_SHIFT; } static inline u8 nvmet_cc_ams(u32 cc) { - return (cc >> NVME_CC_AMS_SHIFT) & 0x7; + return (cc & NVME_CC_AMS_MASK) >> NVME_CC_AMS_SHIFT; } static inline u8 nvmet_cc_shn(u32 cc) { - return (cc >> NVME_CC_SHN_SHIFT) & 0x3; + return (cc & NVME_CC_SHN_MASK) >> NVME_CC_SHN_SHIFT; } static inline u8 nvmet_cc_iosqes(u32 cc) { - return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf; + return (cc & NVME_CC_IOSQES_MASK) >> NVME_CC_IOSQES_SHIFT; } static inline u8 nvmet_cc_iocqes(u32 cc) { - return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf; + return (cc & NVME_CC_IOCQES_MASK) >> NVME_CC_IOCQES_SHIFT; } /* Convert a 32-bit number to a 16-bit 0's based number */ diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c index ac30b42cc622..565d2bd36dcd 100644 --- a/drivers/nvme/target/pci-epf.c +++ b/drivers/nvme/target/pci-epf.c @@ -46,7 +46,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex); /* * BAR CC register and SQ polling intervals. */ -#define NVMET_PCI_EPF_CC_POLL_INTERVAL msecs_to_jiffies(5) +#define NVMET_PCI_EPF_CC_POLL_INTERVAL msecs_to_jiffies(10) #define NVMET_PCI_EPF_SQ_POLL_INTERVAL msecs_to_jiffies(5) #define NVMET_PCI_EPF_SQ_POLL_IDLE msecs_to_jiffies(5000) @@ -1694,6 +1694,7 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work) struct nvmet_pci_epf_ctrl *ctrl = container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work); struct nvmet_pci_epf_queue *sq; + unsigned long limit = jiffies; unsigned long last = 0; int i, nr_sqs; @@ -1708,6 +1709,16 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work) nr_sqs++; } + /* + * If we have been running for a while, reschedule to let other + * tasks run and to avoid RCU stalls. + */ + if (time_is_before_jiffies(limit + secs_to_jiffies(1))) { + cond_resched(); + limit = jiffies; + continue; + } + if (nr_sqs) { last = jiffies; continue; @@ -1822,14 +1833,14 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) if (ctrl->io_sqes < sizeof(struct nvme_command)) { dev_err(ctrl->dev, "Unsupported I/O SQES %zu (need %zu)\n", ctrl->io_sqes, sizeof(struct nvme_command)); - return -EINVAL; + goto err; } ctrl->io_cqes = 1UL << nvmet_cc_iocqes(ctrl->cc); if (ctrl->io_cqes < sizeof(struct nvme_completion)) { dev_err(ctrl->dev, "Unsupported I/O CQES %zu (need %zu)\n", ctrl->io_sqes, sizeof(struct nvme_completion)); - return -EINVAL; + goto err; } /* Create the admin queue. */ @@ -1844,7 +1855,7 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) qsize, pci_addr, 0); if (status != NVME_SC_SUCCESS) { dev_err(ctrl->dev, "Failed to create admin completion queue\n"); - return -EINVAL; + goto err; } qsize = aqa & 0x00000fff; @@ -1854,17 +1865,22 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) if (status != NVME_SC_SUCCESS) { dev_err(ctrl->dev, "Failed to create admin submission queue\n"); nvmet_pci_epf_delete_cq(ctrl->tctrl, 0); - return -EINVAL; + goto err; } ctrl->sq_ab = NVMET_PCI_EPF_SQ_AB; ctrl->irq_vector_threshold = NVMET_PCI_EPF_IV_THRESHOLD; ctrl->enabled = true; + ctrl->csts = NVME_CSTS_RDY; /* Start polling the controller SQs. */ schedule_delayed_work(&ctrl->poll_sqs, 0); return 0; + +err: + ctrl->csts = 0; + return -EINVAL; } static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) @@ -1889,6 +1905,8 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl) /* Delete the admin queue last. */ nvmet_pci_epf_delete_sq(ctrl->tctrl, 0); nvmet_pci_epf_delete_cq(ctrl->tctrl, 0); + + ctrl->csts &= ~NVME_CSTS_RDY; } static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) @@ -1903,19 +1921,19 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) old_cc = ctrl->cc; new_cc = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_CC); + if (new_cc == old_cc) + goto reschedule_work; + ctrl->cc = new_cc; if (nvmet_cc_en(new_cc) && !nvmet_cc_en(old_cc)) { ret = nvmet_pci_epf_enable_ctrl(ctrl); if (ret) - return; - ctrl->csts |= NVME_CSTS_RDY; + goto reschedule_work; } - if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) { + if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) nvmet_pci_epf_disable_ctrl(ctrl); - ctrl->csts &= ~NVME_CSTS_RDY; - } if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) { nvmet_pci_epf_disable_ctrl(ctrl); @@ -1928,6 +1946,7 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work) nvmet_update_cc(ctrl->tctrl, ctrl->cc); nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts); +reschedule_work: schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL); } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 1afd93026f9b..2a4536ef6184 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -996,6 +996,27 @@ out_err: nvmet_req_complete(&cmd->req, status); } +static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue, + struct nvmet_rdma_rsp *rsp) +{ + unsigned long flags; + bool ret = true; + + spin_lock_irqsave(&queue->state_lock, flags); + /* + * recheck queue state is not live to prevent a race condition + * with RDMA_CM_EVENT_ESTABLISHED handler. + */ + if (queue->state == NVMET_RDMA_Q_LIVE) + ret = false; + else if (queue->state == NVMET_RDMA_Q_CONNECTING) + list_add_tail(&rsp->wait_list, &queue->rsp_wait_list); + else + nvmet_rdma_put_rsp(rsp); + spin_unlock_irqrestore(&queue->state_lock, flags); + return ret; +} + static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvmet_rdma_cmd *cmd = @@ -1038,17 +1059,9 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) rsp->n_rdma = 0; rsp->invalidate_rkey = 0; - if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) { - unsigned long flags; - - spin_lock_irqsave(&queue->state_lock, flags); - if (queue->state == NVMET_RDMA_Q_CONNECTING) - list_add_tail(&rsp->wait_list, &queue->rsp_wait_list); - else - nvmet_rdma_put_rsp(rsp); - spin_unlock_irqrestore(&queue->state_lock, flags); + if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) && + nvmet_rdma_recv_not_live(queue, rsp)) return; - } nvmet_rdma_handle_command(queue, rsp); } diff --git a/drivers/platform/cznic/Kconfig b/drivers/platform/cznic/Kconfig index 49c383eb6785..13e37b49d9d0 100644 --- a/drivers/platform/cznic/Kconfig +++ b/drivers/platform/cznic/Kconfig @@ -6,6 +6,7 @@ menuconfig CZNIC_PLATFORMS bool "Platform support for CZ.NIC's Turris hardware" + depends on ARCH_MVEBU || COMPILE_TEST help Say Y here to be able to choose driver support for CZ.NIC's Turris devices. This option alone does not add any kernel code. diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c index fa27195f074e..3c3158f31a48 100644 --- a/drivers/power/supply/axp20x_battery.c +++ b/drivers/power/supply/axp20x_battery.c @@ -466,10 +466,9 @@ static int axp717_battery_get_prop(struct power_supply *psy, /* * If a fault is detected it must also be cleared; if the - * condition persists it should reappear (This is an - * assumption, it's actually not documented). A restart was - * not sufficient to clear the bit in testing despite the - * register listed as POR. + * condition persists it should reappear. A restart was not + * sufficient to clear the bit in testing despite the register + * listed as POR. */ case POWER_SUPPLY_PROP_HEALTH: ret = regmap_read(axp20x_batt->regmap, AXP717_PMU_FAULT, @@ -480,26 +479,26 @@ static int axp717_battery_get_prop(struct power_supply *psy, switch (reg & AXP717_BATT_PMU_FAULT_MASK) { case AXP717_BATT_UVLO_2_5V: val->intval = POWER_SUPPLY_HEALTH_DEAD; - regmap_update_bits(axp20x_batt->regmap, - AXP717_PMU_FAULT, - AXP717_BATT_UVLO_2_5V, - AXP717_BATT_UVLO_2_5V); + regmap_write_bits(axp20x_batt->regmap, + AXP717_PMU_FAULT, + AXP717_BATT_UVLO_2_5V, + AXP717_BATT_UVLO_2_5V); return 0; case AXP717_BATT_OVER_TEMP: val->intval = POWER_SUPPLY_HEALTH_HOT; - regmap_update_bits(axp20x_batt->regmap, - AXP717_PMU_FAULT, - AXP717_BATT_OVER_TEMP, - AXP717_BATT_OVER_TEMP); + regmap_write_bits(axp20x_batt->regmap, + AXP717_PMU_FAULT, + AXP717_BATT_OVER_TEMP, + AXP717_BATT_OVER_TEMP); return 0; case AXP717_BATT_UNDER_TEMP: val->intval = POWER_SUPPLY_HEALTH_COLD; - regmap_update_bits(axp20x_batt->regmap, - AXP717_PMU_FAULT, - AXP717_BATT_UNDER_TEMP, - AXP717_BATT_UNDER_TEMP); + regmap_write_bits(axp20x_batt->regmap, + AXP717_PMU_FAULT, + AXP717_BATT_UNDER_TEMP, + AXP717_BATT_UNDER_TEMP); return 0; default: diff --git a/drivers/power/supply/da9150-fg.c b/drivers/power/supply/da9150-fg.c index 652c1f213af1..4f28ef1bba1a 100644 --- a/drivers/power/supply/da9150-fg.c +++ b/drivers/power/supply/da9150-fg.c @@ -247,9 +247,9 @@ static int da9150_fg_current_avg(struct da9150_fg *fg, DA9150_QIF_SD_GAIN_SIZE); da9150_fg_read_sync_end(fg); - div = (u64) (sd_gain * shunt_val * 65536ULL); + div = 65536ULL * sd_gain * shunt_val; do_div(div, 1000000); - res = (u64) (iavg * 1000000ULL); + res = 1000000ULL * iavg; do_div(res, div); val->intval = (int) res; diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c index d0bb52a7a036..76c340b38015 100644 --- a/drivers/power/supply/power_supply_core.c +++ b/drivers/power/supply/power_supply_core.c @@ -1592,11 +1592,11 @@ __power_supply_register(struct device *parent, if (rc) goto register_thermal_failed; - scoped_guard(rwsem_read, &psy->extensions_sem) { - rc = power_supply_create_triggers(psy); - if (rc) - goto create_triggers_failed; + rc = power_supply_create_triggers(psy); + if (rc) + goto create_triggers_failed; + scoped_guard(rwsem_read, &psy->extensions_sem) { rc = power_supply_add_hwmon_sysfs(psy); if (rc) goto add_hwmon_sysfs_failed; diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index e36e3ea165d3..2f34761e6413 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -588,6 +588,15 @@ out: return ret; } +static void ism_dev_release(struct device *dev) +{ + struct ism_dev *ism; + + ism = container_of(dev, struct ism_dev, dev); + + kfree(ism); +} + static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct ism_dev *ism; @@ -601,6 +610,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id) dev_set_drvdata(&pdev->dev, ism); ism->pdev = pdev; ism->dev.parent = &pdev->dev; + ism->dev.release = ism_dev_release; device_initialize(&ism->dev); dev_set_name(&ism->dev, dev_name(&pdev->dev)); ret = device_add(&ism->dev); @@ -637,7 +647,7 @@ err: device_del(&ism->dev); err_dev: dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); return ret; } @@ -682,7 +692,7 @@ static void ism_remove(struct pci_dev *pdev) pci_disable_device(pdev); device_del(&ism->dev); dev_set_drvdata(&pdev->dev, NULL); - kfree(ism); + put_device(&ism->dev); } static struct pci_driver ism_driver = { diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c index ae42e3a9127f..16913c3ef65c 100644 --- a/drivers/soc/loongson/loongson2_guts.c +++ b/drivers/soc/loongson/loongson2_guts.c @@ -114,8 +114,11 @@ static int loongson2_guts_probe(struct platform_device *pdev) if (of_property_read_string(root, "model", &machine)) of_property_read_string_index(root, "compatible", 0, &machine); of_node_put(root); - if (machine) + if (machine) { soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL); + if (!soc_dev_attr.machine) + return -ENOMEM; + } svr = loongson2_guts_get_svr(); soc_die = loongson2_soc_die_match(svr, loongson2_soc_die); diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c index 322a543b8c27..d0f397c90242 100644 --- a/drivers/tee/optee/supp.c +++ b/drivers/tee/optee/supp.c @@ -80,7 +80,6 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params, struct optee *optee = tee_get_drvdata(ctx->teedev); struct optee_supp *supp = &optee->supp; struct optee_supp_req *req; - bool interruptable; u32 ret; /* @@ -111,36 +110,18 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params, /* * Wait for supplicant to process and return result, once we've * returned from wait_for_completion(&req->c) successfully we have - * exclusive access again. + * exclusive access again. Allow the wait to be killable such that + * the wait doesn't turn into an indefinite state if the supplicant + * gets hung for some reason. */ - while (wait_for_completion_interruptible(&req->c)) { + if (wait_for_completion_killable(&req->c)) { mutex_lock(&supp->mutex); - interruptable = !supp->ctx; - if (interruptable) { - /* - * There's no supplicant available and since the - * supp->mutex currently is held none can - * become available until the mutex released - * again. - * - * Interrupting an RPC to supplicant is only - * allowed as a way of slightly improving the user - * experience in case the supplicant hasn't been - * started yet. During normal operation the supplicant - * will serve all requests in a timely manner and - * interrupting then wouldn't make sense. - */ - if (req->in_queue) { - list_del(&req->link); - req->in_queue = false; - } + if (req->in_queue) { + list_del(&req->link); + req->in_queue = false; } mutex_unlock(&supp->mutex); - - if (interruptable) { - req->ret = TEEC_ERROR_COMMUNICATION; - break; - } + req->ret = TEEC_ERROR_COMMUNICATION; } ret = req->ret; diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6b27db7f9496..0234f14f2aa6 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -875,10 +875,11 @@ struct mm_struct { */ unsigned int nr_cpus_allowed; /** - * @max_nr_cid: Maximum number of concurrency IDs allocated. + * @max_nr_cid: Maximum number of allowed concurrency + * IDs allocated. * - * Track the highest number of concurrency IDs allocated for the - * mm. + * Track the highest number of allowed concurrency IDs + * allocated for the mm. */ atomic_t max_nr_cid; /** diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index c0a86afb85da..ab550a89b9bf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3275,6 +3275,8 @@ static inline struct net_device *first_net_device_rcu(struct net *net) } int netdev_boot_setup_check(struct net_device *dev); +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *hwaddr); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); @@ -4115,7 +4117,6 @@ void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); -void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index e07e8978d691..e435250fcb4d 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -13,6 +13,8 @@ #define NVME_TCP_ADMIN_CCSZ SZ_8K #define NVME_TCP_DIGEST_LENGTH 4 #define NVME_TCP_MIN_MAXH2CDATA 4096 +#define NVME_TCP_MIN_C2HTERM_PLEN 24 +#define NVME_TCP_MAX_C2HTERM_PLEN 152 enum nvme_tcp_pfv { NVME_TCP_PFV_1_0 = 0x0, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index fe3b60818fdc..2dc05b1c3283 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -199,28 +199,54 @@ enum { #define NVME_NVM_IOSQES 6 #define NVME_NVM_IOCQES 4 +/* + * Controller Configuration (CC) register (Offset 14h) + */ enum { + /* Enable (EN): bit 0 */ NVME_CC_ENABLE = 1 << 0, NVME_CC_EN_SHIFT = 0, + + /* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */ + + /* I/O Command Set Selected (CSS): bits 06:04 */ NVME_CC_CSS_SHIFT = 4, - NVME_CC_MPS_SHIFT = 7, - NVME_CC_AMS_SHIFT = 11, - NVME_CC_SHN_SHIFT = 14, - NVME_CC_IOSQES_SHIFT = 16, - NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT, NVME_CC_CSS_NVM = 0 << NVME_CC_CSS_SHIFT, NVME_CC_CSS_CSI = 6 << NVME_CC_CSS_SHIFT, - NVME_CC_CSS_MASK = 7 << NVME_CC_CSS_SHIFT, + + /* Memory Page Size (MPS): bits 10:07 */ + NVME_CC_MPS_SHIFT = 7, + NVME_CC_MPS_MASK = 0xf << NVME_CC_MPS_SHIFT, + + /* Arbitration Mechanism Selected (AMS): bits 13:11 */ + NVME_CC_AMS_SHIFT = 11, + NVME_CC_AMS_MASK = 7 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_RR = 0 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_WRRU = 1 << NVME_CC_AMS_SHIFT, NVME_CC_AMS_VS = 7 << NVME_CC_AMS_SHIFT, + + /* Shutdown Notification (SHN): bits 15:14 */ + NVME_CC_SHN_SHIFT = 14, + NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_NONE = 0 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_NORMAL = 1 << NVME_CC_SHN_SHIFT, NVME_CC_SHN_ABRUPT = 2 << NVME_CC_SHN_SHIFT, - NVME_CC_SHN_MASK = 3 << NVME_CC_SHN_SHIFT, + + /* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */ + NVME_CC_IOSQES_SHIFT = 16, + NVME_CC_IOSQES_MASK = 0xf << NVME_CC_IOSQES_SHIFT, NVME_CC_IOSQES = NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT, + + /* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */ + NVME_CC_IOCQES_SHIFT = 20, + NVME_CC_IOCQES_MASK = 0xf << NVME_CC_IOCQES_SHIFT, NVME_CC_IOCQES = NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT, + + /* Controller Ready Independent of Media Enable (CRIME): bit 24 */ NVME_CC_CRIME = 1 << 24, + + /* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */ }; enum { diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 2cbe0c22a32f..0b9095a281b8 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -91,6 +91,8 @@ struct sk_psock { struct sk_psock_progs progs; #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) struct strparser strp; + u32 copied_seq; + u32 ingress_bytes; #endif struct sk_buff_head ingress_skb; struct list_head ingress_msg; diff --git a/include/net/gro.h b/include/net/gro.h index b9b58c1f8d19..7b548f91754b 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -11,6 +11,9 @@ #include <net/udp.h> #include <net/hotdata.h> +/* This should be increased if a protocol with a bigger head is added. */ +#define GRO_MAX_HEAD (MAX_HEADER + 128) + struct napi_gro_cb { union { struct { diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 7ba1402ca779..f467a66abc6b 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -297,6 +297,7 @@ static inline int check_net(const struct net *net) } void net_drop_ns(void *); +void net_passive_dec(struct net *net); #else @@ -326,8 +327,18 @@ static inline int check_net(const struct net *net) } #define net_drop_ns NULL + +static inline void net_passive_dec(struct net *net) +{ + refcount_dec(&net->passive); +} #endif +static inline void net_passive_inc(struct net *net) +{ + refcount_inc(&net->passive); +} + /* Returns true if the netns initialization is completed successfully */ static inline bool net_initialized(const struct net *net) { diff --git a/include/net/strparser.h b/include/net/strparser.h index 41e2ce9e9e10..0a83010b3a64 100644 --- a/include/net/strparser.h +++ b/include/net/strparser.h @@ -43,6 +43,8 @@ struct strparser; struct strp_callbacks { int (*parse_msg)(struct strparser *strp, struct sk_buff *skb); void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb); + int (*read_sock)(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); int (*read_sock_done)(struct strparser *strp, int err); void (*abort_parser)(struct strparser *strp, int err); void (*lock)(struct strparser *strp); diff --git a/include/net/tcp.h b/include/net/tcp.h index 5b2b04835688..2d08473a6dc0 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -41,6 +41,7 @@ #include <net/inet_ecn.h> #include <net/dst.h> #include <net/mptcp.h> +#include <net/xfrm.h> #include <linux/seq_file.h> #include <linux/memcontrol.h> @@ -683,6 +684,19 @@ void tcp_fin(struct sock *sk); void tcp_check_space(struct sock *sk); void tcp_sack_compress_send_ack(struct sock *sk); +static inline void tcp_cleanup_skb(struct sk_buff *skb) +{ + skb_dst_drop(skb); + secpath_reset(skb); +} + +static inline void tcp_add_receive_queue(struct sock *sk, struct sk_buff *skb) +{ + DEBUG_NET_WARN_ON_ONCE(skb_dst(skb)); + DEBUG_NET_WARN_ON_ONCE(secpath_exists(skb)); + __skb_queue_tail(&sk->sk_receive_queue, skb); +} + /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) @@ -729,6 +743,9 @@ void tcp_get_info(struct sock *, struct tcp_info *); /* Read 'sendfile()'-style from a TCP socket */ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_read_actor_t recv_actor); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq); int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor); struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off); void tcp_read_done(struct sock *sk, size_t len); @@ -2599,6 +2616,11 @@ struct sk_psock; #ifdef CONFIG_BPF_SYSCALL int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore); void tcp_bpf_clone(const struct sock *sk, struct sock *newsk); +#ifdef CONFIG_BPF_STREAM_PARSER +struct strparser; +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor); +#endif /* CONFIG_BPF_STREAM_PARSER */ #endif /* CONFIG_BPF_SYSCALL */ #ifdef CONFIG_INET diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index e11c82638527..050fa8eb2e8f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -380,7 +380,7 @@ enum io_uring_op { * result will be the number of buffers send, with * the starting buffer ID in cqe->flags as per * usual for provided buffer usage. The buffers - * will be contigious from the starting buffer ID. + * will be contiguous from the starting buffer ID. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c index 5d0928f37471..91019b4d0308 100644 --- a/io_uring/io-wq.c +++ b/io_uring/io-wq.c @@ -64,7 +64,7 @@ struct io_worker { union { struct rcu_head rcu; - struct work_struct work; + struct delayed_work work; }; }; @@ -770,6 +770,18 @@ static inline bool io_should_retry_thread(struct io_worker *worker, long err) } } +static void queue_create_worker_retry(struct io_worker *worker) +{ + /* + * We only bother retrying because there's a chance that the + * failure to create a worker is due to some temporary condition + * in the forking task (e.g. outstanding signal); give the task + * some time to clear that condition. + */ + schedule_delayed_work(&worker->work, + msecs_to_jiffies(worker->init_retries * 5)); +} + static void create_worker_cont(struct callback_head *cb) { struct io_worker *worker; @@ -809,12 +821,13 @@ static void create_worker_cont(struct callback_head *cb) /* re-create attempts grab a new worker ref, drop the existing one */ io_worker_release(worker); - schedule_work(&worker->work); + queue_create_worker_retry(worker); } static void io_workqueue_create(struct work_struct *work) { - struct io_worker *worker = container_of(work, struct io_worker, work); + struct io_worker *worker = container_of(work, struct io_worker, + work.work); struct io_wq_acct *acct = io_wq_get_acct(worker); if (!io_queue_worker_create(worker, acct, create_worker_cont)) @@ -855,8 +868,8 @@ fail: kfree(worker); goto fail; } else { - INIT_WORK(&worker->work, io_workqueue_create); - schedule_work(&worker->work); + INIT_DELAYED_WORK(&worker->work, io_workqueue_create); + queue_create_worker_retry(worker); } return true; diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index ceacf6230e34..f7acae5f7e1d 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2045,6 +2045,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->opcode = 0; return io_init_fail_req(req, -EINVAL); } + opcode = array_index_nospec(opcode, IORING_OP_LAST); + def = &io_issue_defs[opcode]; if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { /* enforce forwards compatibility on users */ diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h index 190f7ee45de9..89ea0135a1a0 100644 --- a/io_uring/rsrc.h +++ b/io_uring/rsrc.h @@ -4,12 +4,6 @@ #include <linux/lockdep.h> -#define IO_NODE_ALLOC_CACHE_MAX 32 - -#define IO_RSRC_TAG_TABLE_SHIFT (PAGE_SHIFT - 3) -#define IO_RSRC_TAG_TABLE_MAX (1U << IO_RSRC_TAG_TABLE_SHIFT) -#define IO_RSRC_TAG_TABLE_MASK (IO_RSRC_TAG_TABLE_MAX - 1) - enum { IORING_RSRC_FILE = 0, IORING_RSRC_BUFFER = 1, diff --git a/io_uring/rw.c b/io_uring/rw.c index 7aa1e4c9f64a..9edc6baebd01 100644 --- a/io_uring/rw.c +++ b/io_uring/rw.c @@ -23,6 +23,9 @@ #include "poll.h" #include "rw.h" +static void io_complete_rw(struct kiocb *kiocb, long res); +static void io_complete_rw_iopoll(struct kiocb *kiocb, long res); + struct io_rw { /* NOTE: kiocb has the file as the first member, so don't do it here */ struct kiocb kiocb; @@ -289,6 +292,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, rw->kiocb.dio_complete = NULL; rw->kiocb.ki_flags = 0; + if (req->ctx->flags & IORING_SETUP_IOPOLL) + rw->kiocb.ki_complete = io_complete_rw_iopoll; + else + rw->kiocb.ki_complete = io_complete_rw; + rw->addr = READ_ONCE(sqe->addr); rw->len = READ_ONCE(sqe->len); rw->flags = READ_ONCE(sqe->rw_flags); @@ -563,8 +571,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res) smp_store_release(&req->iopoll_completed, 1); } -static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) +static inline void io_rw_done(struct io_kiocb *req, ssize_t ret) { + struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw); + /* IO was queued async, completion will happen later */ if (ret == -EIOCBQUEUED) return; @@ -586,8 +596,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) } } - INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll, - io_complete_rw, kiocb, ret); + if (req->ctx->flags & IORING_SETUP_IOPOLL) + io_complete_rw_iopoll(&rw->kiocb, ret); + else + io_complete_rw(&rw->kiocb, ret); } static int kiocb_done(struct io_kiocb *req, ssize_t ret, @@ -598,7 +610,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret, if (ret >= 0 && req->flags & REQ_F_CUR_POS) req->file->f_pos = rw->kiocb.ki_pos; - if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) { + if (ret >= 0 && !(req->ctx->flags & IORING_SETUP_IOPOLL)) { __io_complete_rw_common(req, ret); /* * Safe to call io_end from here as we're inline @@ -609,7 +621,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret, io_req_rw_cleanup(req, issue_flags); return IOU_OK; } else { - io_rw_done(&rw->kiocb, ret); + io_rw_done(req, ret); } return IOU_ISSUE_SKIP_COMPLETE; @@ -813,10 +825,8 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) if (ctx->flags & IORING_SETUP_IOPOLL) { if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) return -EOPNOTSUPP; - kiocb->private = NULL; kiocb->ki_flags |= IOCB_HIPRI; - kiocb->ki_complete = io_complete_rw_iopoll; req->iopoll_completed = 0; if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) { /* make sure every req only blocks once*/ @@ -826,7 +836,6 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type) } else { if (kiocb->ki_flags & IOCB_HIPRI) return -EINVAL; - kiocb->ki_complete = io_complete_rw; } if (req->flags & REQ_F_HAS_METADATA) { @@ -904,7 +913,8 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags) } else if (ret == -EIOCBQUEUED) { return IOU_ISSUE_SKIP_COMPLETE; } else if (ret == req->cqe.res || ret <= 0 || !force_nonblock || - (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) { + (req->flags & REQ_F_NOWAIT) || !need_complete_io(req) || + (issue_flags & IO_URING_F_MULTISHOT)) { /* read all, failed, already did sync or don't want to retry */ goto done; } @@ -977,6 +987,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags) if (!io_file_can_poll(req)) return -EBADFD; + /* make it sync, multishot doesn't support async execution */ + rw->kiocb.ki_complete = NULL; ret = __io_read(req, issue_flags); /* diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c index 870aeb51d70a..095a9554e1de 100644 --- a/kernel/bpf/arena.c +++ b/kernel/bpf/arena.c @@ -39,7 +39,7 @@ */ /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ -#define GUARD_SZ (1ull << sizeof_field(struct bpf_insn, off) * 8) +#define GUARD_SZ round_up(1ull << sizeof_field(struct bpf_insn, off) * 8, PAGE_SIZE << 1) #define KERN_VM_SZ (SZ_4G + GUARD_SZ) struct bpf_arena { diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c index d5dc65bb1755..54ff2a85d4c0 100644 --- a/kernel/bpf/bpf_cgrp_storage.c +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -153,7 +153,7 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) static void cgroup_storage_map_free(struct bpf_map *map) { - bpf_local_storage_map_free(map, &cgroup_cache, NULL); + bpf_local_storage_map_free(map, &cgroup_cache, &bpf_cgrp_storage_busy); } /* *gfp_flags* is a hidden argument provided by the verifier */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 9de6acddd479..c3223e0db2f5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6507,6 +6507,8 @@ static const struct bpf_raw_tp_null_args raw_tp_null_args[] = { /* rxrpc */ { "rxrpc_recvdata", 0x1 }, { "rxrpc_resend", 0x10 }, + /* skb */ + {"kfree_skb", 0x1000}, /* sunrpc */ { "xs_stream_read_data", 0x1 }, /* ... from xprt_cong_event event class */ diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index e1cfe890e0be..1499d8caa9a3 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -268,8 +268,6 @@ static int ringbuf_map_mmap_kern(struct bpf_map *map, struct vm_area_struct *vma /* allow writable mapping for the consumer_pos only */ if (vma->vm_pgoff != 0 || vma->vm_end - vma->vm_start != PAGE_SIZE) return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, @@ -289,8 +287,6 @@ static int ringbuf_map_mmap_user(struct bpf_map *map, struct vm_area_struct *vma * position, and the ring buffer data itself. */ return -EPERM; - } else { - vm_flags_clear(vma, VM_MAYWRITE); } /* remap_vmalloc_range() checks size and offset constraints */ return remap_vmalloc_range(vma, rb_map->rb, vma->vm_pgoff + RINGBUF_PGOFF); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c420edbfb7c8..e1e42e918ba7 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1035,7 +1035,7 @@ static const struct vm_operations_struct bpf_map_default_vmops = { static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) { struct bpf_map *map = filp->private_data; - int err; + int err = 0; if (!map->ops->map_mmap || !IS_ERR_OR_NULL(map->record)) return -ENOTSUPP; @@ -1059,24 +1059,33 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma) err = -EACCES; goto out; } + bpf_map_write_active_inc(map); } +out: + mutex_unlock(&map->freeze_mutex); + if (err) + return err; /* set default open/close callbacks */ vma->vm_ops = &bpf_map_default_vmops; vma->vm_private_data = map; vm_flags_clear(vma, VM_MAYEXEC); + /* If mapping is read-only, then disallow potentially re-mapping with + * PROT_WRITE by dropping VM_MAYWRITE flag. This VM_MAYWRITE clearing + * means that as far as BPF map's memory-mapped VMAs are concerned, + * VM_WRITE and VM_MAYWRITE and equivalent, if one of them is set, + * both should be set, so we can forget about VM_MAYWRITE and always + * check just VM_WRITE + */ if (!(vma->vm_flags & VM_WRITE)) - /* disallow re-mapping with PROT_WRITE */ vm_flags_clear(vma, VM_MAYWRITE); err = map->ops->map_mmap(map, vma); - if (err) - goto out; + if (err) { + if (vma->vm_flags & VM_WRITE) + bpf_map_write_active_dec(map); + } - if (vma->vm_flags & VM_MAYWRITE) - bpf_map_write_active_inc(map); -out: - mutex_unlock(&map->freeze_mutex); return err; } @@ -1968,8 +1977,6 @@ int generic_map_update_batch(struct bpf_map *map, struct file *map_file, return err; } -#define MAP_LOOKUP_RETRIES 3 - int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr) @@ -1979,8 +1986,8 @@ int generic_map_lookup_batch(struct bpf_map *map, void __user *values = u64_to_user_ptr(attr->batch.values); void __user *keys = u64_to_user_ptr(attr->batch.keys); void *buf, *buf_prevkey, *prev_key, *key, *value; - int err, retry = MAP_LOOKUP_RETRIES; u32 value_size, cp, max_count; + int err; if (attr->batch.elem_flags & ~BPF_F_LOCK) return -EINVAL; @@ -2026,14 +2033,8 @@ int generic_map_lookup_batch(struct bpf_map *map, err = bpf_map_copy_value(map, key, value, attr->batch.elem_flags); - if (err == -ENOENT) { - if (retry) { - retry--; - continue; - } - err = -EINTR; - break; - } + if (err == -ENOENT) + goto next_key; if (err) goto free_buf; @@ -2048,12 +2049,12 @@ int generic_map_lookup_batch(struct bpf_map *map, goto free_buf; } + cp++; +next_key: if (!prev_key) prev_key = buf_prevkey; swap(prev_key, key); - retry = MAP_LOOKUP_RETRIES; - cp++; cond_resched(); } diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9971c03adfd5..60611df77957 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1501,6 +1501,8 @@ static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum r struct bpf_reference_state *s; s = acquire_reference_state(env, insn_idx); + if (!s) + return -ENOMEM; s->type = type; s->id = id; s->ptr = ptr; @@ -9149,10 +9151,11 @@ static int check_reg_const_str(struct bpf_verifier_env *env, return 0; } -/* Returns constant key value if possible, else negative error */ -static s64 get_constant_map_key(struct bpf_verifier_env *env, +/* Returns constant key value in `value` if possible, else negative error */ +static int get_constant_map_key(struct bpf_verifier_env *env, struct bpf_reg_state *key, - u32 key_size) + u32 key_size, + s64 *value) { struct bpf_func_state *state = func(env, key); struct bpf_reg_state *reg; @@ -9179,8 +9182,10 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env, /* First handle precisely tracked STACK_ZERO */ for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--) zero_size++; - if (zero_size >= key_size) + if (zero_size >= key_size) { + *value = 0; return 0; + } /* Check that stack contains a scalar spill of expected size */ if (!is_spilled_scalar_reg(&state->stack[spi])) @@ -9203,9 +9208,12 @@ static s64 get_constant_map_key(struct bpf_verifier_env *env, if (err < 0) return err; - return reg->var_off.value; + *value = reg->var_off.value; + return 0; } +static bool can_elide_value_nullness(enum bpf_map_type type); + static int check_func_arg(struct bpf_verifier_env *env, u32 arg, struct bpf_call_arg_meta *meta, const struct bpf_func_proto *fn, @@ -9354,9 +9362,16 @@ skip_type_check: err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL); if (err) return err; - meta->const_map_key = get_constant_map_key(env, reg, key_size); - if (meta->const_map_key < 0 && meta->const_map_key != -EOPNOTSUPP) - return meta->const_map_key; + if (can_elide_value_nullness(meta->map_ptr->map_type)) { + err = get_constant_map_key(env, reg, key_size, &meta->const_map_key); + if (err < 0) { + meta->const_map_key = -1; + if (err == -EOPNOTSUPP) + err = 0; + else + return err; + } + } break; case ARG_PTR_TO_MAP_VALUE: if (type_may_be_null(arg_type) && register_is_null(reg)) diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c index fbe34299673d..10b63433f057 100644 --- a/kernel/cgroup/dmem.c +++ b/kernel/cgroup/dmem.c @@ -220,60 +220,32 @@ dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool, struct dmem_cgroup_pool_state *test_pool) { struct page_counter *climit; - struct cgroup_subsys_state *css, *next_css; + struct cgroup_subsys_state *css; struct dmemcg_state *dmemcg_iter; - struct dmem_cgroup_pool_state *pool, *parent_pool; - bool found_descendant; + struct dmem_cgroup_pool_state *pool, *found_pool; climit = &limit_pool->cnt; rcu_read_lock(); - parent_pool = pool = limit_pool; - css = &limit_pool->cs->css; - /* - * This logic is roughly equivalent to css_foreach_descendant_pre, - * except we also track the parent pool to find out which pool we need - * to calculate protection values for. - * - * We can stop the traversal once we find test_pool among the - * descendants since we don't really care about any others. - */ - while (pool != test_pool) { - next_css = css_next_child(NULL, css); - if (next_css) { - parent_pool = pool; - } else { - while (css != &limit_pool->cs->css) { - next_css = css_next_child(css, css->parent); - if (next_css) - break; - css = css->parent; - parent_pool = pool_parent(parent_pool); - } - /* - * We can only hit this when test_pool is not a - * descendant of limit_pool. - */ - if (WARN_ON_ONCE(css == &limit_pool->cs->css)) - break; - } - css = next_css; - - found_descendant = false; + css_for_each_descendant_pre(css, &limit_pool->cs->css) { dmemcg_iter = container_of(css, struct dmemcg_state, css); + found_pool = NULL; list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) { - if (pool_parent(pool) == parent_pool) { - found_descendant = true; + if (pool->region == limit_pool->region) { + found_pool = pool; break; } } - if (!found_descendant) + if (!found_pool) continue; page_counter_calculate_protection( - climit, &pool->cnt, true); + climit, &found_pool->cnt, true); + + if (found_pool == test_pool) + break; } rcu_read_unlock(); } diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 2ca797cbe465..bf2a87a0a378 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -417,7 +417,7 @@ static void update_ref_ctr_warn(struct uprobe *uprobe, struct mm_struct *mm, short d) { pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " - "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", + "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%p\n", d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) uprobe->ref_ctr_offset, mm); diff --git a/kernel/rseq.c b/kernel/rseq.c index 442aba29bc4c..2cb16091ec0a 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -507,9 +507,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EINVAL; if (!access_ok(rseq, rseq_len)) return -EFAULT; - current->rseq = rseq; - current->rseq_len = rseq_len; - current->rseq_sig = sig; #ifdef CONFIG_DEBUG_RSEQ /* * Initialize the in-kernel rseq fields copy for validation of @@ -522,6 +519,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, return -EFAULT; #endif /* + * Activate the registration by setting the rseq area address, length + * and signature in the task struct. + */ + current->rseq = rseq; + current->rseq_len = rseq_len; + current->rseq_sig = sig; + + /* * If rseq was previously inactive, and has just been * registered, ensure the cpu_id_start and cpu_id fields * are updated before returning to user-space. diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b93c8c3dc05a..c8512a9fb022 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) { struct cpumask *cidmask = mm_cidmask(mm); struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid; - int cid = __this_cpu_read(pcpu_cid->recent_cid); + int cid, max_nr_cid, allowed_max_nr_cid; + /* + * After shrinking the number of threads or reducing the number + * of allowed cpus, reduce the value of max_nr_cid so expansion + * of cid allocation will preserve cache locality if the number + * of threads or allowed cpus increase again. + */ + max_nr_cid = atomic_read(&mm->max_nr_cid); + while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed), + atomic_read(&mm->mm_users))), + max_nr_cid > allowed_max_nr_cid) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */ + if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) { + max_nr_cid = allowed_max_nr_cid; + break; + } + } /* Try to re-use recent cid. This improves cache locality. */ - if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask)) + cid = __this_cpu_read(pcpu_cid->recent_cid); + if (!mm_cid_is_unset(cid) && cid < max_nr_cid && + !cpumask_test_and_set_cpu(cid, cidmask)) return cid; /* * Expand cid allocation if the maximum number of concurrency @@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm) * and number of threads. Expanding cid allocation as much as * possible improves cache locality. */ - cid = atomic_read(&mm->max_nr_cid); + cid = max_nr_cid; while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) { + /* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */ if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1)) continue; if (!cpumask_test_and_set_cpu(cid, cidmask)) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 2560b312ad57..33082c4e8154 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -403,13 +403,12 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num) lockdep_assert_held(&fprobe_mutex); fprobe_graph_active--; - if (!fprobe_graph_active) { - /* Q: should we unregister it ? */ + /* Q: should we unregister it ? */ + if (!fprobe_graph_active) unregister_ftrace_graph(&fprobe_graph_ops); - return; - } - ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); + if (num) + ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0); } static int symbols_cmp(const void *a, const void *b) @@ -679,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp) } del_fprobe_hash(fp); - if (count) - fprobe_graph_remove_ips(addrs, count); + fprobe_graph_remove_ips(addrs, count); kfree_rcu(hlist_array, rcu); fp->hlist_array = NULL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 728ecda6e8d4..6b0c25761ccb 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src) * The filter_hash updates uses just the append_hash() function * and the notrace_hash does not. */ -static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash) +static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash, + int size_bits) { struct ftrace_func_entry *entry; int size; int i; - /* An empty hash does everything */ - if (ftrace_hash_empty(*hash)) - return 0; + if (*hash) { + /* An empty hash does everything */ + if (ftrace_hash_empty(*hash)) + return 0; + } else { + *hash = alloc_ftrace_hash(size_bits); + if (!*hash) + return -ENOMEM; + } /* If new_hash has everything make hash have everything */ if (ftrace_hash_empty(new_hash)) { @@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has /* Return a new hash that has a union of all @ops->filter_hash entries */ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) { - struct ftrace_hash *new_hash; + struct ftrace_hash *new_hash = NULL; struct ftrace_ops *subops; + int size_bits; int ret; - new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits); - if (!new_hash) - return NULL; + if (ops->func_hash->filter_hash) + size_bits = ops->func_hash->filter_hash->size_bits; + else + size_bits = FTRACE_HASH_DEFAULT_BITS; list_for_each_entry(subops, &ops->subop_list, list) { - ret = append_hash(&new_hash, subops->func_hash->filter_hash); + ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits); if (ret < 0) { free_ftrace_hash(new_hash); return NULL; @@ -3310,7 +3319,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops) if (ftrace_hash_empty(new_hash)) break; } - return new_hash; + /* Can't return NULL as that means this failed */ + return new_hash ? : EMPTY_HASH; } /* Make @ops trace evenything except what all its subops do not trace */ @@ -3505,7 +3515,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash); if (!filter_hash) return -ENOMEM; - ret = append_hash(&filter_hash, subops->func_hash->filter_hash); + ret = append_hash(&filter_hash, subops->func_hash->filter_hash, + size_bits); if (ret < 0) { free_ftrace_hash(filter_hash); return ret; @@ -5707,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) return -ENOENT; free_hash_entry(hash, entry); return 0; + } else if (__ftrace_lookup_ip(hash, ip) != NULL) { + /* Already exists */ + return 0; } entry = add_hash_entry(hash, ip); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 4cb275316e51..513de9ceb80e 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos) return iter; #endif + /* + * The iter is allocated in s_start() and passed via the 'v' + * parameter. To stop the iterator, NULL must be returned. But + * the return value is what the 'v' parameter in s_stop() receives + * and frees. Free iter here as it will no longer be used. + */ + kfree(iter); return NULL; } @@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v) } #endif -static void s_stop(struct seq_file *m, void *p) +static void s_stop(struct seq_file *m, void *v) { - kfree(p); + kfree(v); t_stop(m, NULL); } diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index d358c9935164..df56f9b76010 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip, parent_ip = function_get_true_parent_ip(parent_ip, fregs); - trace_ctx = tracing_gen_ctx(); + trace_ctx = tracing_gen_ctx_dec(); data = this_cpu_ptr(tr->array_buffer.data); if (!atomic_read(&data->disabled)) @@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, struct trace_array *tr = op->private; struct trace_array_cpu *data; unsigned int trace_ctx; - unsigned long flags; int bit; if (unlikely(!tr->function_enabled)) @@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip, if (is_repeat_check(tr, last_info, ip, parent_ip)) goto out; - local_save_flags(flags); - trace_ctx = tracing_gen_ctx_flags(flags); + trace_ctx = tracing_gen_ctx_dec(); process_repeats(tr, ip, parent_ip, last_info, trace_ctx); trace_function(tr, ip, parent_ip, trace_ctx); diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 8f6f7db48d4e..7cb192cbd65f 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -660,12 +660,9 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 user_size, void __user *data_in = u64_to_user_ptr(kattr->test.data_in); void *data; - if (size < ETH_HLEN || size > PAGE_SIZE - headroom - tailroom) + if (user_size < ETH_HLEN || user_size > PAGE_SIZE - headroom - tailroom) return ERR_PTR(-EINVAL); - if (user_size > size) - return ERR_PTR(-EMSGSIZE); - size = SKB_DATA_ALIGN(size); data = kzalloc(size + headroom + tailroom, GFP_USER); if (!data) diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 7d41cde1bcca..2e538399757f 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -355,11 +355,6 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { - const struct btf *btf_vmlinux; - const struct btf_type *t; - const char *tname; - u32 btf_id; - if (prog->aux->dst_prog) return false; @@ -374,13 +369,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: - btf_vmlinux = bpf_get_btf_vmlinux(); - if (IS_ERR_OR_NULL(btf_vmlinux)) - return false; - btf_id = prog->aux->attach_btf_id; - t = btf_type_by_id(btf_vmlinux, btf_id); - tname = btf_name_by_offset(btf_vmlinux, t->name_off); - return !!strncmp(tname, "bpf_sk_storage", + return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; diff --git a/net/core/dev.c b/net/core/dev.c index b91658e8aedb..1b252e9459fd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1121,6 +1121,12 @@ out: return ret; } +static bool dev_addr_cmp(struct net_device *dev, unsigned short type, + const char *ha) +{ + return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); +} + /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace @@ -1129,7 +1135,7 @@ out: * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. - * The caller must hold RCU or RTNL. + * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * @@ -1141,14 +1147,39 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, struct net_device *dev; for_each_netdev_rcu(net, dev) - if (dev->type == type && - !memcmp(dev->dev_addr, ha, dev->addr_len)) + if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); +/** + * dev_getbyhwaddr() - find a device by its hardware address + * @net: the applicable net namespace + * @type: media type of device + * @ha: hardware address + * + * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold + * rtnl_lock. + * + * Context: rtnl_lock() must be held. + * Return: pointer to the net_device, or NULL if not found + */ +struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, + const char *ha) +{ + struct net_device *dev; + + ASSERT_RTNL(); + for_each_netdev(net, dev) + if (dev_addr_cmp(dev, type, ha)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_getbyhwaddr); + struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; @@ -2070,6 +2101,42 @@ static void __move_netdevice_notifier_net(struct net *src_net, __register_netdevice_notifier_net(dst_net, nb, true); } +static void rtnl_net_dev_lock(struct net_device *dev) +{ + bool again; + + do { + struct net *net; + + again = false; + + /* netns might be being dismantled. */ + rcu_read_lock(); + net = dev_net_rcu(dev); + net_passive_inc(net); + rcu_read_unlock(); + + rtnl_net_lock(net); + +#ifdef CONFIG_NET_NS + /* dev might have been moved to another netns. */ + if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { + rtnl_net_unlock(net); + net_passive_dec(net); + again = true; + } +#endif + } while (again); +} + +static void rtnl_net_dev_unlock(struct net_device *dev) +{ + struct net *net = dev_net(dev); + + rtnl_net_unlock(net); + net_passive_dec(net); +} + int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) @@ -2077,6 +2144,11 @@ int register_netdevice_notifier_dev_net(struct net_device *dev, struct net *net = dev_net(dev); int err; + /* rtnl_net_lock() assumes dev is not yet published by + * register_netdevice(). + */ + DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list)); + rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); if (!err) { @@ -2093,13 +2165,12 @@ int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { - struct net *net = dev_net(dev); int err; - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); list_del(&nn->list); - err = __unregister_netdevice_notifier_net(net, nb); - rtnl_net_unlock(net); + err = __unregister_netdevice_notifier_net(dev_net(dev), nb); + rtnl_net_dev_unlock(dev); return err; } @@ -6920,6 +6991,23 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } +/* Double check that napi_get_frags() allocates skbs with + * skb->head being backed by slab, not a page fragment. + * This is to make sure bug fixed in 3226b158e67c + * ("net: avoid 32 x truesize under-estimation for tiny skbs") + * does not accidentally come back. + */ +static void napi_get_frags_check(struct napi_struct *napi) +{ + struct sk_buff *skb; + + local_bh_disable(); + skb = napi_get_frags(napi); + WARN_ON_ONCE(skb && skb->head_frag); + napi_free_frags(napi); + local_bh_enable(); +} + void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), @@ -11880,11 +11968,9 @@ EXPORT_SYMBOL(unregister_netdevice_many); */ void unregister_netdev(struct net_device *dev) { - struct net *net = dev_net(dev); - - rtnl_net_lock(net); + rtnl_net_dev_lock(dev); unregister_netdevice(dev); - rtnl_net_unlock(net); + rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 6efd4cccc9dd..212f0a048cab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1734,30 +1734,30 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - rc = genl_register_family(&net_drop_monitor_family); - if (rc) { - pr_err("Could not create drop monitor netlink family\n"); - return rc; + for_each_possible_cpu(cpu) { + net_dm_cpu_data_init(cpu); + net_dm_hw_cpu_data_init(cpu); } - WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = register_netdevice_notifier(&dropmon_net_notifier); if (rc < 0) { pr_crit("Failed to register netdevice notifier\n"); + return rc; + } + + rc = genl_register_family(&net_drop_monitor_family); + if (rc) { + pr_err("Could not create drop monitor netlink family\n"); goto out_unreg; } + WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT); rc = 0; - for_each_possible_cpu(cpu) { - net_dm_cpu_data_init(cpu); - net_dm_hw_cpu_data_init(cpu); - } - goto out; out_unreg: - genl_unregister_family(&net_drop_monitor_family); + WARN_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); out: return rc; } @@ -1766,19 +1766,18 @@ static void exit_net_drop_monitor(void) { int cpu; - BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); - /* * Because of the module_get/put we do in the trace state change path * we are guaranteed not to have any current users when we get here */ + BUG_ON(genl_unregister_family(&net_drop_monitor_family)); + + BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier)); for_each_possible_cpu(cpu) { net_dm_hw_cpu_data_fini(cpu); net_dm_cpu_data_fini(cpu); } - - BUG_ON(genl_unregister_family(&net_drop_monitor_family)); } module_init(init_net_drop_monitor); diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 5db41bf2ed93..9cd8de6bebb5 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -853,23 +853,30 @@ __skb_flow_dissect_ports(const struct sk_buff *skb, void *target_container, const void *data, int nhoff, u8 ip_proto, int hlen) { - enum flow_dissector_key_id dissector_ports = FLOW_DISSECTOR_KEY_MAX; - struct flow_dissector_key_ports *key_ports; + struct flow_dissector_key_ports_range *key_ports_range = NULL; + struct flow_dissector_key_ports *key_ports = NULL; + __be32 ports; if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS; - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - dissector_ports = FLOW_DISSECTOR_KEY_PORTS_RANGE; + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); - if (dissector_ports == FLOW_DISSECTOR_KEY_MAX) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS_RANGE)) + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + + if (!key_ports && !key_ports_range) return; - key_ports = skb_flow_dissector_target(flow_dissector, - dissector_ports, - target_container); - key_ports->ports = __skb_flow_get_ports(skb, nhoff, ip_proto, - data, hlen); + ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen); + + if (key_ports) + key_ports->ports = ports; + + if (key_ports_range) + key_ports_range->tp.ports = ports; } static void @@ -924,6 +931,7 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, struct flow_dissector *flow_dissector, void *target_container) { + struct flow_dissector_key_ports_range *key_ports_range = NULL; struct flow_dissector_key_ports *key_ports = NULL; struct flow_dissector_key_control *key_control; struct flow_dissector_key_basic *key_basic; @@ -968,20 +976,21 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } - if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { key_ports = skb_flow_dissector_target(flow_dissector, FLOW_DISSECTOR_KEY_PORTS, target_container); - else if (dissector_uses_key(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE)) - key_ports = skb_flow_dissector_target(flow_dissector, - FLOW_DISSECTOR_KEY_PORTS_RANGE, - target_container); - - if (key_ports) { key_ports->src = flow_keys->sport; key_ports->dst = flow_keys->dport; } + if (dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE)) { + key_ports_range = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS_RANGE, + target_container); + key_ports_range->tp.src = flow_keys->sport; + key_ports_range->tp.dst = flow_keys->dport; + } if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_FLOW_LABEL)) { diff --git a/net/core/gro.c b/net/core/gro.c index d1f44084e978..78b320b63174 100644 --- a/net/core/gro.c +++ b/net/core/gro.c @@ -7,9 +7,6 @@ #define MAX_GRO_SKBS 8 -/* This should be increased if a protocol with a bigger head is added. */ -#define GRO_MAX_HEAD (MAX_HEADER + 128) - static DEFINE_SPINLOCK(offload_lock); /** diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index cb39a12b2f82..4303f2a49262 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -464,7 +464,7 @@ static void net_complete_free(void) } -static void net_free(struct net *net) +void net_passive_dec(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); @@ -482,7 +482,7 @@ void net_drop_ns(void *p) struct net *net = (struct net *)p; if (net) - net_free(net); + net_passive_dec(net); } struct net *copy_net_ns(unsigned long flags, @@ -523,7 +523,7 @@ put_userns: key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); - net_free(net); + net_passive_dec(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); @@ -672,7 +672,7 @@ static void cleanup_net(struct work_struct *work) key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); - net_free(net); + net_passive_dec(net); } cleanup_net_task = NULL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a441613a1e6c..7b03b64fdcb2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -69,6 +69,7 @@ #include <net/dst.h> #include <net/sock.h> #include <net/checksum.h> +#include <net/gro.h> #include <net/gso.h> #include <net/hotdata.h> #include <net/ip6_checksum.h> @@ -95,7 +96,9 @@ static struct kmem_cache *skbuff_ext_cache __ro_after_init; #endif -#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(MAX_TCP_HEADER) +#define GRO_MAX_HEAD_PAD (GRO_MAX_HEAD + NET_SKB_PAD + NET_IP_ALIGN) +#define SKB_SMALL_HEAD_SIZE SKB_HEAD_ALIGN(max(MAX_TCP_HEADER, \ + GRO_MAX_HEAD_PAD)) /* We want SKB_SMALL_HEAD_CACHE_SIZE to not be a power of two. * This should ensure that SKB_SMALL_HEAD_HEADROOM is a unique @@ -220,67 +223,9 @@ static void skb_under_panic(struct sk_buff *skb, unsigned int sz, void *addr) #define NAPI_SKB_CACHE_BULK 16 #define NAPI_SKB_CACHE_HALF (NAPI_SKB_CACHE_SIZE / 2) -#if PAGE_SIZE == SZ_4K - -#define NAPI_HAS_SMALL_PAGE_FRAG 1 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) ((nc).pfmemalloc) - -/* specialized page frag allocator using a single order 0 page - * and slicing it into 1K sized fragment. Constrained to systems - * with a very limited amount of 1K fragments fitting a single - * page - to avoid excessive truesize underestimation - */ - -struct page_frag_1k { - void *va; - u16 offset; - bool pfmemalloc; -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp) -{ - struct page *page; - int offset; - - offset = nc->offset - SZ_1K; - if (likely(offset >= 0)) - goto use_frag; - - page = alloc_pages_node(NUMA_NO_NODE, gfp, 0); - if (!page) - return NULL; - - nc->va = page_address(page); - nc->pfmemalloc = page_is_pfmemalloc(page); - offset = PAGE_SIZE - SZ_1K; - page_ref_add(page, offset / SZ_1K); - -use_frag: - nc->offset = offset; - return nc->va + offset; -} -#else - -/* the small page is actually unused in this build; add dummy helpers - * to please the compiler and avoid later preprocessor's conditionals - */ -#define NAPI_HAS_SMALL_PAGE_FRAG 0 -#define NAPI_SMALL_PAGE_PFMEMALLOC(nc) false - -struct page_frag_1k { -}; - -static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask) -{ - return NULL; -} - -#endif - struct napi_alloc_cache { local_lock_t bh_lock; struct page_frag_cache page; - struct page_frag_1k page_small; unsigned int skb_count; void *skb_cache[NAPI_SKB_CACHE_SIZE]; }; @@ -290,23 +235,6 @@ static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; -/* Double check that napi_get_frags() allocates skbs with - * skb->head being backed by slab, not a page fragment. - * This is to make sure bug fixed in 3226b158e67c - * ("net: avoid 32 x truesize under-estimation for tiny skbs") - * does not accidentally come back. - */ -void napi_get_frags_check(struct napi_struct *napi) -{ - struct sk_buff *skb; - - local_bh_disable(); - skb = napi_get_frags(napi); - WARN_ON_ONCE(!NAPI_HAS_SMALL_PAGE_FRAG && skb && skb->head_frag); - napi_free_frags(napi); - local_bh_enable(); -} - void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); @@ -736,7 +664,7 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. */ - if (len <= SKB_WITH_OVERHEAD(1024) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE); @@ -813,10 +741,8 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) /* If requested length is either too small or too big, * we use kmalloc() for skb->head allocation. - * When the small frag allocator is available, prefer it over kmalloc - * for small fragments */ - if ((!NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) || + if (len <= SKB_WITH_OVERHEAD(SKB_SMALL_HEAD_CACHE_SIZE) || len > SKB_WITH_OVERHEAD(PAGE_SIZE) || (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) { skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX | SKB_ALLOC_NAPI, @@ -826,32 +752,16 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len) goto skb_success; } + len = SKB_HEAD_ALIGN(len); + if (sk_memalloc_socks()) gfp_mask |= __GFP_MEMALLOC; local_lock_nested_bh(&napi_alloc_cache.bh_lock); nc = this_cpu_ptr(&napi_alloc_cache); - if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) { - /* we are artificially inflating the allocation size, but - * that is not as bad as it may look like, as: - * - 'len' less than GRO_MAX_HEAD makes little sense - * - On most systems, larger 'len' values lead to fragment - * size above 512 bytes - * - kmalloc would use the kmalloc-1k slab for such values - * - Builds with smaller GRO_MAX_HEAD will very likely do - * little networking, as that implies no WiFi and no - * tunnels support, and 32 bits arches. - */ - len = SZ_1K; - data = page_frag_alloc_1k(&nc->page_small, gfp_mask); - pfmemalloc = NAPI_SMALL_PAGE_PFMEMALLOC(nc->page_small); - } else { - len = SKB_HEAD_ALIGN(len); - - data = page_frag_alloc(&nc->page, len, gfp_mask); - pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); - } + data = page_frag_alloc(&nc->page, len, gfp_mask); + pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page); local_unlock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!data)) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 61f3f3d4e528..0ddc4c718833 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -549,6 +549,9 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb, return num_sge; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) + psock->ingress_bytes += len; +#endif copied = len; msg->sg.start = 0; msg->sg.size = copied; @@ -1144,6 +1147,10 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) if (!ret) sk_psock_set_state(psock, SK_PSOCK_RX_STRP_ENABLED); + if (sk_is_tcp(sk)) { + psock->strp.cb.read_sock = tcp_bpf_strp_read_sock; + psock->copied_seq = tcp_sk(sk)->copied_seq; + } return ret; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f1b9b3958792..82a14f131d00 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -303,7 +303,10 @@ static int sock_map_link(struct bpf_map *map, struct sock *sk) write_lock_bh(&sk->sk_callback_lock); if (stream_parser && stream_verdict && !psock->saved_data_ready) { - ret = sk_psock_init_strp(sk, psock); + if (sk_is_tcp(sk)) + ret = sk_psock_init_strp(sk, psock); + else + ret = -EOPNOTSUPP; if (ret) { write_unlock_bh(&sk->sk_callback_lock); sk_psock_put(sk, psock); @@ -541,6 +544,9 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN); if (sk_is_stream_unix(sk)) return (1 << sk->sk_state) & TCPF_ESTABLISHED; + if (sk_is_vsock(sk) && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) + return (1 << sk->sk_state) & TCPF_ESTABLISHED; return true; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f23a1ec6694c..814300eee39d 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1077,7 +1077,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, __be32 mask = ((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0d704bda6c41..285678d8ce07 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1565,12 +1565,13 @@ EXPORT_SYMBOL(tcp_recv_skb); * or for 'peeking' the socket using this routine * (although both would be easy to implement). */ -int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, - sk_read_actor_t recv_actor) +static int __tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) { struct sk_buff *skb; struct tcp_sock *tp = tcp_sk(sk); - u32 seq = tp->copied_seq; + u32 seq = *copied_seq; u32 offset; int copied = 0; @@ -1624,9 +1625,12 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_eat_recv_skb(sk, skb); if (!desc->count) break; - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); } - WRITE_ONCE(tp->copied_seq, seq); + WRITE_ONCE(*copied_seq, seq); + + if (noack) + goto out; tcp_rcv_space_adjust(sk); @@ -1635,10 +1639,25 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, tcp_recv_skb(sk, seq, &offset); tcp_cleanup_rbuf(sk, copied); } +out: return copied; } + +int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + return __tcp_read_sock(sk, desc, recv_actor, false, + &tcp_sk(sk)->copied_seq); +} EXPORT_SYMBOL(tcp_read_sock); +int tcp_read_sock_noack(struct sock *sk, read_descriptor_t *desc, + sk_read_actor_t recv_actor, bool noack, + u32 *copied_seq) +{ + return __tcp_read_sock(sk, desc, recv_actor, noack, copied_seq); +} + int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) { struct sk_buff *skb; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 47f65b1b70ca..ba581785adb4 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -646,6 +646,42 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops) ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP; } +#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER) +int tcp_bpf_strp_read_sock(struct strparser *strp, read_descriptor_t *desc, + sk_read_actor_t recv_actor) +{ + struct sock *sk = strp->sk; + struct sk_psock *psock; + struct tcp_sock *tp; + int copied = 0; + + tp = tcp_sk(sk); + rcu_read_lock(); + psock = sk_psock(sk); + if (WARN_ON_ONCE(!psock)) { + desc->error = -EINVAL; + goto out; + } + + psock->ingress_bytes = 0; + copied = tcp_read_sock_noack(sk, desc, recv_actor, true, + &psock->copied_seq); + if (copied < 0) + goto out; + /* recv_actor may redirect skb to another socket (SK_REDIRECT) or + * just put skb into ingress queue of current socket (SK_PASS). + * For SK_REDIRECT, we need to ack the frame immediately but for + * SK_PASS, we want to delay the ack until tcp_bpf_recvmsg_parser(). + */ + tp->copied_seq = psock->copied_seq - psock->ingress_bytes; + tcp_rcv_space_adjust(sk); + __tcp_cleanup_rbuf(sk, copied - psock->ingress_bytes); +out: + rcu_read_unlock(); + return copied; +} +#endif /* CONFIG_BPF_STREAM_PARSER */ + int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) { int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 0f523cbfe329..32b28fc21b63 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -178,7 +178,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) if (!skb) return; - skb_dst_drop(skb); + tcp_cleanup_skb(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects @@ -195,7 +195,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index eb82e01da911..0cbf81bf3d45 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -243,9 +243,15 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) do_div(val, skb->truesize); tcp_sk(sk)->scaling_ratio = val ? val : 1; - if (old_ratio != tcp_sk(sk)->scaling_ratio) - WRITE_ONCE(tcp_sk(sk)->window_clamp, - tcp_win_from_space(sk, sk->sk_rcvbuf)); + if (old_ratio != tcp_sk(sk)->scaling_ratio) { + struct tcp_sock *tp = tcp_sk(sk); + + val = tcp_win_from_space(sk, sk->sk_rcvbuf); + tcp_set_window_clamp(sk, val); + + if (tp->window_clamp < tp->rcvq_space.space) + tp->rcvq_space.space = tp->window_clamp; + } } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len, tcp_sk(sk)->advmss); @@ -4970,7 +4976,7 @@ static void tcp_ofo_queue(struct sock *sk) tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN; if (!eaten) - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); else kfree_skb_partial(skb, fragstolen); @@ -5162,7 +5168,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, skb, fragstolen)) ? 1 : 0; tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq); if (!eaten) { - __skb_queue_tail(&sk->sk_receive_queue, skb); + tcp_add_receive_queue(sk, skb); skb_set_owner_r(skb, sk); } return eaten; @@ -5245,7 +5251,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); return; } - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); reason = SKB_DROP_REASON_NOT_SPECIFIED; @@ -6226,7 +6232,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPHITS); /* Bulk data transfer: receiver */ - skb_dst_drop(skb); + tcp_cleanup_skb(skb); __skb_pull(skb, tcp_header_len); eaten = tcp_queue_rcv(sk, skb, &fragstolen); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cc2b5194a18d..2632844d2c35 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2027,7 +2027,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, */ skb_condense(skb); - skb_dst_drop(skb); + tcp_cleanup_skb(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 8e47e5355be6..4f648af8cfaa 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -97,7 +97,7 @@ tcf_exts_miss_cookie_base_alloc(struct tcf_exts *exts, struct tcf_proto *tp, err = xa_alloc_cyclic(&tcf_exts_miss_cookies_xa, &n->miss_cookie_base, n, xa_limit_32b, &next, GFP_KERNEL); - if (err) + if (err < 0) goto err_xa_alloc; exts->miss_cookie_node = n; diff --git a/net/sctp/stream.c b/net/sctp/stream.c index c241cc552e8d..bfcff6d6a438 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -735,7 +735,7 @@ struct sctp_chunk *sctp_process_strreset_tsnreq( * value SHOULD be the smallest TSN not acknowledged by the * receiver of the request plus 2^31. */ - init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1 << 31); + init_tsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map) + (1U << 31); sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, init_tsn, GFP_ATOMIC); diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 8299ceb3e373..95696f42647e 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -347,7 +347,10 @@ static int strp_read_sock(struct strparser *strp) struct socket *sock = strp->sk->sk_socket; read_descriptor_t desc; - if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) + if (unlikely(!sock || !sock->ops)) + return -EBUSY; + + if (unlikely(!strp->cb.read_sock && !sock->ops->read_sock)) return -EBUSY; desc.arg.data = strp; @@ -355,7 +358,10 @@ static int strp_read_sock(struct strparser *strp) desc.count = 1; /* give more than one skb per call */ /* sk should be locked here, so okay to do read_sock */ - sock->ops->read_sock(strp->sk, &desc, strp_recv); + if (strp->cb.read_sock) + strp->cb.read_sock(strp, &desc, strp_recv); + else + sock->ops->read_sock(strp->sk, &desc, strp_recv); desc.error = strp->cb.read_sock_done(strp, desc.error); @@ -468,6 +474,7 @@ int strp_init(struct strparser *strp, struct sock *sk, strp->cb.unlock = cb->unlock ? : strp_sock_unlock; strp->cb.rcv_msg = cb->rcv_msg; strp->cb.parse_msg = cb->parse_msg; + strp->cb.read_sock = cb->read_sock; strp->cb.read_sock_done = cb->read_sock_done ? : default_read_sock_done; strp->cb.abort_parser = cb->abort_parser ? : strp_abort_strp; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 53a081d49d28..7e3db87ae433 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1189,6 +1189,9 @@ static int vsock_read_skb(struct sock *sk, skb_read_actor_t read_actor) { struct vsock_sock *vsk = vsock_sk(sk); + if (WARN_ON_ONCE(!vsk->transport)) + return -ENODEV; + return vsk->transport->read_skb(vsk, read_actor); } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index b58c3818f284..f0e48e6911fc 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -670,6 +670,13 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) }; int ret; + mutex_lock(&vsock->rx_lock); + vsock->rx_buf_nr = 0; + vsock->rx_buf_max_nr = 0; + mutex_unlock(&vsock->rx_lock); + + atomic_set(&vsock->queued_replies, 0); + ret = virtio_find_vqs(vdev, VSOCK_VQ_MAX, vsock->vqs, vqs_info, NULL); if (ret < 0) return ret; @@ -779,9 +786,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->vdev = vdev; - vsock->rx_buf_nr = 0; - vsock->rx_buf_max_nr = 0; - atomic_set(&vsock->queued_replies, 0); mutex_init(&vsock->tx_lock); mutex_init(&vsock->rx_lock); diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index f201d9eca1df..07b96d56f3a5 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -87,7 +87,7 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, lock_sock(sk); vsk = vsock_sk(sk); - if (!vsk->transport) { + if (WARN_ON_ONCE(!vsk->transport)) { copied = -ENODEV; goto out; } diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c index 66191ae9863c..79c3ccadb962 100644 --- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c @@ -120,11 +120,12 @@ static void validate_fetch_results(int outer_map_fd, static void fetch_and_validate(int outer_map_fd, struct bpf_map_batch_opts *opts, - __u32 batch_size, bool delete_entries) + __u32 batch_size, bool delete_entries, + bool has_holes) { - __u32 *fetched_keys, *fetched_values, total_fetched = 0; - __u32 batch_key = 0, fetch_count, step_size; - int err, max_entries = OUTER_MAP_ENTRIES; + int err, max_entries = OUTER_MAP_ENTRIES - !!has_holes; + __u32 *fetched_keys, *fetched_values, total_fetched = 0, i; + __u32 batch_key = 0, fetch_count, step_size = batch_size; __u32 value_size = sizeof(__u32); /* Total entries needs to be fetched */ @@ -134,9 +135,8 @@ static void fetch_and_validate(int outer_map_fd, "Memory allocation failed for fetched_keys or fetched_values", "error=%s\n", strerror(errno)); - for (step_size = batch_size; - step_size <= max_entries; - step_size += batch_size) { + /* hash map may not always return full batch */ + for (i = 0; i < OUTER_MAP_ENTRIES; i++) { fetch_count = step_size; err = delete_entries ? bpf_map_lookup_and_delete_batch(outer_map_fd, @@ -155,6 +155,7 @@ static void fetch_and_validate(int outer_map_fd, if (err && errno == ENOSPC) { /* Fetch again with higher batch size */ total_fetched = 0; + step_size += batch_size; continue; } @@ -184,18 +185,19 @@ static void fetch_and_validate(int outer_map_fd, } static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, - enum bpf_map_type inner_map_type) + enum bpf_map_type inner_map_type, + bool has_holes) { + __u32 max_entries = OUTER_MAP_ENTRIES - !!has_holes; __u32 *outer_map_keys, *inner_map_fds; - __u32 max_entries = OUTER_MAP_ENTRIES; LIBBPF_OPTS(bpf_map_batch_opts, opts); __u32 value_size = sizeof(__u32); int batch_size[2] = {5, 10}; __u32 map_index, op_index; int outer_map_fd, ret; - outer_map_keys = calloc(max_entries, value_size); - inner_map_fds = calloc(max_entries, value_size); + outer_map_keys = calloc(OUTER_MAP_ENTRIES, value_size); + inner_map_fds = calloc(OUTER_MAP_ENTRIES, value_size); CHECK((!outer_map_keys || !inner_map_fds), "Memory allocation failed for outer_map_keys or inner_map_fds", "error=%s\n", strerror(errno)); @@ -209,6 +211,24 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, ((outer_map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) ? 9 : 1000) - map_index; + /* This condition is only meaningful for array of maps. + * + * max_entries == OUTER_MAP_ENTRIES - 1 if it is true. Say + * max_entries is short for n, then outer_map_keys looks like: + * + * [n, n-1, ... 2, 1] + * + * We change it to + * + * [n, n-1, ... 2, 0] + * + * So it will leave key 1 as a hole. It will serve to test the + * correctness when batch on an array: a "non-exist" key might be + * actually allocated and returned from key iteration. + */ + if (has_holes) + outer_map_keys[max_entries - 1]--; + /* batch operation - map_update */ ret = bpf_map_update_batch(outer_map_fd, outer_map_keys, inner_map_fds, &max_entries, &opts); @@ -219,15 +239,17 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, /* batch operation - map_lookup */ for (op_index = 0; op_index < 2; ++op_index) fetch_and_validate(outer_map_fd, &opts, - batch_size[op_index], false); + batch_size[op_index], false, + has_holes); /* batch operation - map_lookup_delete */ if (outer_map_type == BPF_MAP_TYPE_HASH_OF_MAPS) fetch_and_validate(outer_map_fd, &opts, - max_entries, true /*delete*/); + max_entries, true /*delete*/, + has_holes); /* close all map fds */ - for (map_index = 0; map_index < max_entries; map_index++) + for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++) close(inner_map_fds[map_index]); close(outer_map_fd); @@ -237,16 +259,20 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, void test_map_in_map_batch_ops_array(void) { - _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, false); printf("%s:PASS with inner ARRAY map\n", __func__); - _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, false); printf("%s:PASS with inner HASH map\n", __func__); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, true); + printf("%s:PASS with inner ARRAY map with holes\n", __func__); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, true); + printf("%s:PASS with inner HASH map with holes\n", __func__); } void test_map_in_map_batch_ops_hash(void) { - _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY); + _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY, false); printf("%s:PASS with inner ARRAY map\n", __func__); - _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH); + _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH, false); printf("%s:PASS with inner HASH map\n", __func__); } diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c index 3729fbfd3084..80b153d3ddec 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -542,8 +542,12 @@ static void detach_program(struct bpf_flow *skel, int prog_fd) static int set_port_drop(int pf, bool multi_port) { + char dst_port[16]; + + snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER); + SYS(fail, "tc qdisc add dev lo ingress"); - SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s", + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s", "dev lo", "parent FFFF:", "protocol", pf == PF_INET6 ? "ipv6" : "ip", @@ -551,6 +555,7 @@ static int set_port_drop(int pf, bool multi_port) "flower", "ip_proto udp", "src_port", multi_port ? "8-10" : "9", + "dst_port", dst_port, "action drop"); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 884ad87783d5..1e3e4392dcca 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -111,31 +111,35 @@ out: static void test_sockmap_vsock_delete_on_close(void) { - int err, c, p, map; - const int zero = 0; - - err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); - if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) - return; + int map, c, p, err, zero = 0; map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (!ASSERT_GE(map, 0, "bpf_map_create")) { - close(c); - goto out; - } + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; - err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); - close(c); - if (!ASSERT_OK(err, "bpf_map_update")) - goto out; + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; + + if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST)) + goto close_socks; + + xclose(c); + xclose(p); + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); ASSERT_OK(err, "after close(), bpf_map_update"); -out: - close(p); - close(map); +close_socks: + xclose(c); + xclose(p); +close_map: + xclose(map); } static void test_skmsg_helpers(enum bpf_map_type map_type) @@ -522,8 +526,8 @@ static void test_sockmap_skb_verdict_shutdown(void) if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) goto out_close; - n = recv(c1, &b, 1, SOCK_NONBLOCK); - ASSERT_EQ(n, 0, "recv_timeout(fin)"); + n = recv(c1, &b, 1, MSG_DONTWAIT); + ASSERT_EQ(n, 0, "recv(fin)"); out_close: close(c1); close(p1); @@ -531,57 +535,6 @@ out: test_sockmap_pass_prog__destroy(skel); } -static void test_sockmap_stream_pass(void) -{ - int zero = 0, sent, recvd; - int verdict, parser; - int err, map; - int c = -1, p = -1; - struct test_sockmap_pass_prog *pass = NULL; - char snd[256] = "0123456789"; - char rcv[256] = "0"; - - pass = test_sockmap_pass_prog__open_and_load(); - verdict = bpf_program__fd(pass->progs.prog_skb_verdict); - parser = bpf_program__fd(pass->progs.prog_skb_parser); - map = bpf_map__fd(pass->maps.sock_map_rx); - - err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0); - if (!ASSERT_OK(err, "bpf_prog_attach stream parser")) - goto out; - - err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); - if (!ASSERT_OK(err, "bpf_prog_attach stream verdict")) - goto out; - - err = create_pair(AF_INET, SOCK_STREAM, &c, &p); - if (err) - goto out; - - /* sk_data_ready of 'p' will be replaced by strparser handler */ - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); - if (!ASSERT_OK(err, "bpf_map_update_elem(p)")) - goto out_close; - - /* - * as 'prog_skb_parser' return the original skb len and - * 'prog_skb_verdict' return SK_PASS, the kernel will just - * pass it through to original socket 'p' - */ - sent = xsend(c, snd, sizeof(snd), 0); - ASSERT_EQ(sent, sizeof(snd), "xsend(c)"); - - recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK, - IO_TIMEOUT_SEC); - ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)"); - -out_close: - close(c); - close(p); - -out: - test_sockmap_pass_prog__destroy(pass); -} static void test_sockmap_skb_verdict_fionread(bool pass_prog) { @@ -628,7 +581,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog) ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); /* On DROP test there will be no data to read */ if (pass_prog) { - recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC); ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); } @@ -1061,6 +1014,34 @@ destroy: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_vsock_unconnected(void) +{ + struct sockaddr_storage addr; + int map, s, zero = 0; + socklen_t alen; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; + + s = xsocket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) + goto close_map; + + /* Fail connect(), but trigger transport assignment. */ + init_addr_loopback(AF_VSOCK, &addr, &alen); + if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect")) + goto close_sock; + + ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update"); + +close_sock: + xclose(s); +close_map: + xclose(map); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1101,8 +1082,6 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); if (test__start_subtest("sockmap skb_verdict shutdown")) test_sockmap_skb_verdict_shutdown(); - if (test__start_subtest("sockmap stream parser and verdict pass")) - test_sockmap_stream_pass(); if (test__start_subtest("sockmap skb_verdict fionread")) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) @@ -1127,4 +1106,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); if (test__start_subtest("sockmap skb_verdict vsock poll")) test_sockmap_skb_verdict_vsock_poll(); + if (test__start_subtest("sockmap vsock unconnected")) + test_sockmap_vsock_unconnected(); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c new file mode 100644 index 000000000000..621b3b71888e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <netinet/tcp.h> +#include <test_progs.h> +#include "sockmap_helpers.h" +#include "test_skmsg_load_helpers.skel.h" +#include "test_sockmap_strp.skel.h" + +#define STRP_PKT_HEAD_LEN 4 +#define STRP_PKT_BODY_LEN 6 +#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN) + +static const char packet[STRP_PKT_FULL_LEN] = "head+body\0"; +static const int test_packet_num = 100; + +/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready + * with sk held if an skb exists in sk_receive_queue. Then for the + * data_ready implementation of strparser, it will delay the read + * operation if sk is held and EAGAIN is returned. + */ +static int sockmap_strp_consume_pre_data(int p) +{ + int recvd; + bool retried = false; + char rcv[10]; + +retry: + errno = 0; + recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1); + if (recvd < 0 && errno == EAGAIN && retried == false) { + /* On the first call, EAGAIN will certainly be returned. + * A 1-second wait is enough for the workqueue to finish. + */ + sleep(1); + retried = true; + goto retry; + } + + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "data mismatch")) + return -1; + return 0; +} + +static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass, + bool need_parser) +{ + struct test_sockmap_strp *strp = NULL; + int verdict, parser; + int err; + + strp = test_sockmap_strp__open_and_load(); + *out_map = bpf_map__fd(strp->maps.sock_map); + + if (need_parser) + parser = bpf_program__fd(strp->progs.prog_skb_parser_partial); + else + parser = bpf_program__fd(strp->progs.prog_skb_parser); + + if (pass) + verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass); + else + verdict = bpf_program__fd(strp->progs.prog_skb_verdict); + + err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (!ASSERT_OK(err, "bpf_prog_attach stream parser")) + goto err; + + err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach stream verdict")) + goto err; + + return strp; +err: + test_sockmap_strp__destroy(strp); + return NULL; +} + +/* Dispatch packets to different socket by packet size: + * + * ------ ------ + * | pkt4 || pkt1 |... > remote socket + * ------ ------ / ------ ------ + * | pkt8 | pkt7 |... + * ------ ------ \ ------ ------ + * | pkt3 || pkt2 |... > local socket + * ------ ------ + */ +static void test_sockmap_strp_dispatch_pkt(int family, int sotype) +{ + int i, j, zero = 0, one = 1, recvd; + int err, map; + int c0 = -1, p0 = -1, c1 = -1, p1 = -1; + struct test_sockmap_strp *strp = NULL; + int test_cnt = 6; + char rcv[10]; + struct { + char data[7]; + int data_len; + int send_cnt; + int *receiver; + } send_dir[2] = { + /* data expected to deliver to local */ + {"llllll", 6, 0, &p0}, + /* data expected to deliver to remote */ + {"rrrrr", 5, 0, &c1} + }; + + strp = sockmap_strp_init(&map, false, false); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p0)")) + goto out_close; + + err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p1)")) + goto out_close; + + err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero)); + if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)")) + goto out_close; + + /* deliver data with data size greater than 5 to local */ + strp->data->verdict_max_size = 5; + + for (i = 0; i < test_cnt; i++) { + int d = i % 2; + + xsend(c0, send_dir[d].data, send_dir[d].data_len, 0); + send_dir[d].send_cnt++; + } + + for (i = 0; i < 2; i++) { + for (j = 0; j < send_dir[i].send_cnt; j++) { + int expected = send_dir[i].data_len; + + recvd = recv_timeout(*send_dir[i].receiver, rcv, + expected, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, expected, "recv_timeout()")) + goto out_close; + if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd), + "data mismatch")) + goto out_close; + } + } +out_close: + close(c0); + close(c1); + close(p0); + close(p1); +out: + test_sockmap_strp__destroy(strp); +} + +/* We have multiple packets in one skb + * ------------ ------------ ------------ + * | packet1 | packet2 | ... + * ------------ ------------ ------------ + */ +static void test_sockmap_strp_multiple_pkt(int family, int sotype) +{ + int i, zero = 0; + int sent, recvd, total; + int err, map; + int c = -1, p = -1; + struct test_sockmap_strp *strp = NULL; + char *snd = NULL, *rcv = NULL; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)")) + goto out_close; + + /* construct multiple packets in one buffer */ + total = test_packet_num * STRP_PKT_FULL_LEN; + snd = malloc(total); + rcv = malloc(total + 1); + if (!ASSERT_TRUE(snd, "malloc(snd)") || + !ASSERT_TRUE(rcv, "malloc(rcv)")) + goto out_close; + + for (i = 0; i < test_packet_num; i++) { + memcpy(snd + i * STRP_PKT_FULL_LEN, + packet, STRP_PKT_FULL_LEN); + } + + sent = xsend(c, snd, total, 0); + if (!ASSERT_EQ(sent, total, "xsend(c)")) + goto out_close; + + /* try to recv one more byte to avoid truncation check */ + recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, total, "recv(rcv)")) + goto out_close; + + /* we sent TCP segment with multiple encapsulation + * then check whether packets are handled correctly + */ + if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch")) + goto out_close; + +out_close: + close(c); + close(p); + if (snd) + free(snd); + if (rcv) + free(rcv); +out: + test_sockmap_strp__destroy(strp); +} + +/* Test strparser with partial read */ +static void test_sockmap_strp_partial_read(int family, int sotype) +{ + int zero = 0, recvd, off; + int err, map; + int c = -1, p = -1; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + /* sk_data_ready of 'p' will be replaced by strparser handler */ + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)")) + goto out_close; + + /* 1.1 send partial head, 1 byte header left */ + off = STRP_PKT_HEAD_LEN - 1; + xsend(c, packet, off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data")) + goto out_close; + + /* 1.2 send remaining head and body */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data")) + goto out_close; + + /* 2.1 send partial head, 1 byte header left */ + off = STRP_PKT_HEAD_LEN - 1; + xsend(c, packet, off, 0); + + /* 2.2 send remaining head and partial body, 1 byte body left */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0); + off = STRP_PKT_FULL_LEN - 1; + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data")) + goto out_close; + + /* 2.3 send remaining body */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data")) + goto out_close; + +out_close: + close(c); + close(p); + +out: + test_sockmap_strp__destroy(strp); +} + +/* Test simple socket read/write with strparser + FIONREAD */ +static void test_sockmap_strp_pass(int family, int sotype, bool fionread) +{ + int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail; + int err, map; + int c = -1, p = -1; + int test_cnt = 10, i; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + /* inject some data before bpf process, it should be read + * correctly because we check sk_receive_queue in + * tcp_bpf_recvmsg_parser(). + */ + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)")) + goto out_close; + + /* sk_data_ready of 'p' will be replaced by strparser handler */ + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p)")) + goto out_close; + + /* consume previous data we injected */ + if (sockmap_strp_consume_pre_data(p)) + goto out_close; + + /* Previously, we encountered issues such as deadlocks and + * sequence errors that resulted in the inability to read + * continuously. Therefore, we perform multiple iterations + * of testing here. + */ + for (i = 0; i < test_cnt; i++) { + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "xsend(c)")) + goto out_close; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") || + !ASSERT_OK(memcmp(packet, rcv, pkt_size), + "memcmp, data mismatch")) + goto out_close; + } + + if (fionread) { + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)")) + goto out_close; + + err = ioctl(p, FIONREAD, &avail); + if (!ASSERT_OK(err, "ioctl(FIONREAD) error") || + !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)")) + goto out_close; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") || + !ASSERT_OK(memcmp(packet, rcv, pkt_size), + "second memcmp, data mismatch")) + goto out_close; + } + +out_close: + close(c); + close(p); + +out: + test_sockmap_strp__destroy(strp); +} + +/* Test strparser with verdict mode */ +static void test_sockmap_strp_verdict(int family, int sotype) +{ + int zero = 0, one = 1, sent, recvd, off; + int err, map; + int c0 = -1, p0 = -1, c1 = -1, p1 = -1; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, false, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + /* We simulate a reverse proxy server. + * When p0 receives data from c0, we forward it to c1. + * From c1's perspective, it will consider this data + * as being sent by p1. + */ + err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p0)")) + goto out_close; + + err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p1)")) + goto out_close; + + sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0); + if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)")) + goto out_close; + + recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "received data does not match the sent data")) + goto out_close; + + /* send again to ensure the stream is functioning correctly. */ + sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0); + if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)")) + goto out_close; + + /* partial read */ + off = STRP_PKT_FULL_LEN / 2; + recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "partial received data does not match the sent data")) + goto out_close; + +out_close: + close(c0); + close(c1); + close(p0); + close(p1); +out: + test_sockmap_strp__destroy(strp); +} + +void test_sockmap_strp(void) +{ + if (test__start_subtest("sockmap strp tcp pass")) + test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false); + if (test__start_subtest("sockmap strp tcp v6 pass")) + test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false); + if (test__start_subtest("sockmap strp tcp pass fionread")) + test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true); + if (test__start_subtest("sockmap strp tcp v6 pass fionread")) + test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true); + if (test__start_subtest("sockmap strp tcp verdict")) + test_sockmap_strp_verdict(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp v6 verdict")) + test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp partial read")) + test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp multiple packets")) + test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp dispatch")) + test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index c7f74f068e78..df27535995af 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* send a packet to trigger any potential bugs in there */ - char data[10] = {}; + char data[ETH_HLEN] = {}; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 27ffed17d4be..461ab18705d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void) __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd; struct nstoken *nstoken = NULL; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); @@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void) struct nstoken *nstoken = NULL; __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c new file mode 100644 index 000000000000..dde3d5bec515 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +int verdict_max_size = 10000; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map SEC(".maps"); + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict(struct __sk_buff *skb) +{ + __u32 one = 1; + + if (skb->len > verdict_max_size) + return SK_PASS; + + return bpf_sk_redirect_map(skb, &sock_map, one, 0); +} + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict_pass(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_skb/stream_parser") +int prog_skb_parser(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb/stream_parser") +int prog_skb_parser_partial(struct __sk_buff *skb) +{ + /* agreement with the test program on a 4-byte size header + * and 6-byte body. + */ + if (skb->len < 4) { + /* need more header to determine full length */ + return 0; + } + /* return full length decoded from header. + * the return value may be larger than skb->len which + * means framework must wait body coming. + */ + return 10; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c index 29eb9568633f..0a187ff725cc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_array_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c @@ -713,4 +713,19 @@ unsigned int non_stack_key_lookup(void) return val->index; } +SEC("socket") +__description("doesn't reject UINT64_MAX as s64 for irrelevant maps") +__success __retval(42) +unsigned int doesnt_reject_irrelevant_maps(void) +{ + __u64 key = 0xFFFFFFFFFFFFFFFF; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_hash_48b, &key); + if (val) + return val->index; + + return 42; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc index dc25bcf4f9e2..449f9d8be746 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc @@ -7,12 +7,38 @@ echo 0 > events/enable echo > dynamic_events PLACE=$FUNCTION_FORK +PLACE2="kmem_cache_free" +PLACE3="schedule_timeout" echo "f:myevent1 $PLACE" >> dynamic_events + +# Make sure the event is attached and is the only one +grep -q $PLACE enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + echo "f:myevent2 $PLACE%return" >> dynamic_events +# It should till be the only attached function +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + +# add another event +echo "f:myevent3 $PLACE2" >> dynamic_events + +grep -q $PLACE2 enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 2 ]; then + exit_fail +fi + grep -q myevent1 dynamic_events grep -q myevent2 dynamic_events +grep -q myevent3 dynamic_events test -d events/fprobes/myevent1 test -d events/fprobes/myevent2 @@ -21,6 +47,34 @@ echo "-:myevent2" >> dynamic_events grep -q myevent1 dynamic_events ! grep -q myevent2 dynamic_events +# should still have 2 left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 2 ]; then + exit_fail +fi + echo > dynamic_events +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo "f:myevent4 $PLACE" >> dynamic_events + +# Should only have one enabled +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 1 ]; then + exit_fail +fi + +echo > dynamic_events + +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne 0 ]; then + exit_fail +fi + clear_trace diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh index 3885a2a91f7d..baed5e380dae 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -20,6 +20,7 @@ ALL_TESTS=" test_port_range_ipv4_tcp test_port_range_ipv6_udp test_port_range_ipv6_tcp + test_port_range_ipv4_udp_drop " NUM_NETIFS=4 @@ -194,6 +195,51 @@ test_port_range_ipv6_tcp() __test_port_range $proto $ip_proto $sip $dip $mode "$name" } +test_port_range_ipv4_udp_drop() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP Drop" + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=2000 + local sport_max=3000 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport=5000 + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport \ + action drop + + # Test ports outside range - should pass + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport" + + # Test ports inside range - should be dropped + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport" + + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Filter did not drop the expected number of packets" + + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + setup_prepare() { h1=${NETIFS[p1]} |